Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,12 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+assets/Emmanuel_English.wav filter=lfs diff=lfs merge=lfs -text
+assets/Emmanuel_Hausa.wav filter=lfs diff=lfs merge=lfs -text
+assets/Eniola_English.wav filter=lfs diff=lfs merge=lfs -text
+assets/Eniola_Hausa.wav filter=lfs diff=lfs merge=lfs -text
+assets/Eniola_Igbo.wav filter=lfs diff=lfs merge=lfs -text
+assets/Eniola_Yoruba.wav filter=lfs diff=lfs merge=lfs -text
+assets/Lovelyn_English.wav filter=lfs diff=lfs merge=lfs -text
+assets/Lovelyn_Igbo.wav filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,654 @@
+---
+library_name: transformers
+tags:
+- voice-cloning
+- audio
+- unsloth
+- orpheus
+- snac
+- hypaai
+- lora
+- merged
+license: apache-2.0
+datasets:
+- hypaai/Hypa_Fleurs
+- MrDragonFox/Elise
+- canopylabs/zac-sample-dataset
+- google/fleurs
+language:
+- ig
+- yo
+- ha
+- en
+base_model:
+- canopylabs/orpheus-3b-0.1-ft
+pipeline_tag: text-to-speech
+---
+
+# Hypa_Orpheus-3b-0.1-ft (merged 16-bit)
+
+A 16-bit quantized and merged, memory-efficient fine-tuned version of [`canopylabs/orpheus-3b-0.1-ft`](https://huggingface.co/canopylabs/orpheus-3b-0.1-ft), optimized with Unsloth and LoRA, for expressive multilingual TTS, especially in low-resource African languages. This model provides the following capabilities:
+
+* Text-to-Speech generation
+* Speech synthesis for under-represented accents
+* Voice cloning & emotion synthesis
+* Research on multilingual low-resource voice AI
+
+Check out the model at [`HypaChat`](https://hypachat.com/)
+
+---
+
+## Model Details
+
+### Model Summary
+
+This model was trained on a parallel text-speech dataset totaling over 300 hours (75k samples) of Nigerian-accented and low-resource language audio (Igbo, Yoruba, Hausa). A key part of the dataset comes from AfroVoices' transcription of real-world YouTube data (denoted as Random speaker, ~100+ hrs).
+To preserve and enhance multilingual capabilities while avoiding catastrophic forgetting, we included synthetic speech-text data sampled from the original 8 Orpheus voices using the default emotional prompts.
+The final training set also included new speakers like:
+* Eniola (40 hrs) – Female, bold, clear
+* Moyo (40 hrs) – Female, professional, articulate
+* Lovelyn (35 hrs) – Female, warm, shy
+* Precious (30 hrs) – Female, friendly, gentle
+
+This model sets state-of-the-art performance on low-resource Multilingual TTS tasks across African languages (see training stats below).
+
+### Base Model Details
+
+The default Orpheus-TTS model released by [`Canopy Labs`](https://canopylabs.ai/releases/orpheus_can_speak_any_language) supports the below voices and emotions:
+
+Voices: `tara`, `leah`, `jess`, `leo`, `dan`, `mia`, `zac`, and `zoe`.
+
+Emotions: `<laugh>`, `<chuckle>`, `<sigh>`, `<cough>`, `<sniffle>`, `<groan>`, `<yawn>`, and `<gasp>`.
+
+Through synthetic data generation and addition, our finetuned model also maintains these voices and emotions. Please visit the default model's card for mor info on voices and emotions.
+
+### Our Model Sample Generations
+
+🎧 Listen to samples generated by Hypa Orpheus-TTS
+
+<div style="margin-top: 20px;">
+<table style="width: 100%; border-collapse: collapse;">
+  <thead>
+    <tr>
+        <th style="border: 1px solid #ddd; padding: 8px; width: 30%;">Text Input</th>
+        <th style="border: 1px solid #ddd; padding: 8px; width: 40%;">Audio Output</th>
+        <th style="border: 1px solid #ddd; padding: 8px; width: 10%;">Language</th>
+        <th style="border: 1px solid #ddd; padding: 8px; width: 10%;">Voice</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+        <td style="border: 1px solid #ddd; padding: 8px;">I am cooking for guests tomorrow and need to know how to make aioli. Can you give me a step-by-step recipe.</td>
+        <td style="border: 1px solid #ddd; padding: 8px;">
+            <audio controls style="width: 100%;">
+                <source src="https://huggingface.co/hypaai/Hypa_Orpheus-3b-0.1-ft-unsloth-bnb-4bit/resolve/main/assets/Emmanuel_English.wav" type="audio/wav">
+            </audio>
+        </td>
+        <td style="border: 1px solid #ddd; padding: 8px;">English</td>
+        <td style="border: 1px solid #ddd; padding: 8px;">Emmanuel</td>
+    </tr>
+    <tr>
+        <td style="border: 1px solid #ddd; padding: 8px;">Ina dafa abinci don bakin gobe kuma ina bukatar sanin yadda ake yin ailoli. Za ka iya ba ni girke-gireken matakan daya bayan daya?</td>
+        <td style="border: 1px solid #ddd; padding: 8px;">
+            <audio controls style="width: 100%;">
+                <source src="https://huggingface.co/hypaai/Hypa_Orpheus-3b-0.1-ft-unsloth-bnb-4bit/resolve/main/assets/Emmanuel_Hausa.wav" type="audio/wav">
+            </audio>
+        </td>
+        <td style="border: 1px solid #ddd; padding: 8px;">Hausa</td>
+        <td style="border: 1px solid #ddd; padding: 8px;">Emmanuel</td>
+    </tr>
+    <tr>
+        <td style="border: 1px solid #ddd; padding: 8px;">Ina dafa abinci don bakin gobe kuma ina bukatar sanin yadda ake yin ailoli. Za ka iya ba ni girke-gireken matakan daya bayan daya?</td>
+        <td style="border: 1px solid #ddd; padding: 8px;">
+            <audio controls style="width: 100%;">
+                <source src="https://huggingface.co/hypaai/Hypa_Orpheus-3b-0.1-ft-unsloth-bnb-4bit/resolve/main/assets/Eniola_Hausa.wav" type="audio/wav">
+            </audio>
+        </td>
+        <td style="border: 1px solid #ddd; padding: 8px;">Hausa</td>
+        <td style="border: 1px solid #ddd; padding: 8px;">Eniola</td>
+    </tr>
+    <tr>
+        <td style="border: 1px solid #ddd; padding: 8px;">Èmi máa se o��njẹ fún àwọn àlejò l'ọ́la mo sì nílò láti mọ bí wọn ti ńṣe aioli. Ṣe o lè fún mi ni àwọn ìlànà ìdáná ẹlẹ́sẹẹsẹ?</td>
+        <td style="border: 1px solid #ddd; padding: 8px;">
+            <audio controls style="width: 100%;">
+                <source src="https://huggingface.co/hypaai/Hypa_Orpheus-3b-0.1-ft-unsloth-bnb-4bit/resolve/main/assets/Eniola_Yoruba.wav" type="audio/wav">
+            </audio>
+        </td>
+        <td style="border: 1px solid #ddd; padding: 8px;">Yoruba</td>
+        <td style="border: 1px solid #ddd; padding: 8px;">Eniola</td>
+    </tr>
+    <tr>
+        <td style="border: 1px solid #ddd; padding: 8px;">I am cooking for guests tomorrow and need to know how to make aioli. Can you give me a step-by-step recipe.</td>
+        <td style="border: 1px solid #ddd; padding: 8px;">
+            <audio controls style="width: 100%;">
+                <source src="https://huggingface.co/hypaai/Hypa_Orpheus-3b-0.1-ft-unsloth-bnb-4bit/resolve/main/assets/Eniola_English.wav" type="audio/wav">
+            </audio>
+        </td>
+        <td style="border: 1px solid #ddd; padding: 8px;">English</td>
+        <td style="border: 1px solid #ddd; padding: 8px;">Eniola</td>
+    </tr>
+    <tr>
+        <td style="border: 1px solid #ddd; padding: 8px;">M na-esi nri maka ndị ọbịa echi ma achọ ịmata otú esi esi aioli. Ị nwere ike inye m usoro ntụziaka?</td>
+        <td style="border: 1px solid #ddd; padding: 8px;">
+            <audio controls style="width: 100%;">
+                <source src="https://huggingface.co/hypaai/Hypa_Orpheus-3b-0.1-ft-unsloth-bnb-4bit/resolve/main/assets/Eniola_Igbo.wav" type="audio/wav">
+            </audio>
+        </td>
+        <td style="border: 1px solid #ddd; padding: 8px;">Igbo</td>
+        <td style="border: 1px solid #ddd; padding: 8px;">Eniola</td>
+    </tr>
+    <tr>
+        <td style="border: 1px solid #ddd; padding: 8px;">M na-esi nri maka ndị ọbịa echi ma achọ ịmata otú esi esi aioli. Ị nwere ike inye m usoro ntụziaka?</td>
+        <td style="border: 1px solid #ddd; padding: 8px;">
+            <audio controls style="width: 100%;">
+                <source src="https://huggingface.co/hypaai/Hypa_Orpheus-3b-0.1-ft-unsloth-bnb-4bit/resolve/main/assets/Lovelyn_Igbo.wav" type="audio/wav">
+            </audio>
+        </td>
+        <td style="border: 1px solid #ddd; padding: 8px;">Igbo</td>
+        <td style="border: 1px solid #ddd; padding: 8px;">Lovelyn</td>
+    </tr>
+    <tr>
+        <td style="border: 1px solid #ddd; padding: 8px;">I am cooking for guests tomorrow and need to know how to make aioli. Can you give me a step-by-step recipe.</td>
+        <td style="border: 1px solid #ddd; padding: 8px;">
+            <audio controls style="width: 100%;">
+                <source src="https://huggingface.co/hypaai/Hypa_Orpheus-3b-0.1-ft-unsloth-bnb-4bit/resolve/main/assets/Lovelyn_English.wav" type="audio/wav">
+            </audio>
+        </td>
+        <td style="border: 1px solid #ddd; padding: 8px;">English</td>
+        <td style="border: 1px solid #ddd; padding: 8px;">Lovelyn</td>
+    </tr>
+  </tbody>
+</table>
+</div>
+
+---
+
+## Training Details
+
+### Training Summary
+
+* Base model: canopylabs/orpheus-3b-0.1-ft
+* Training engine: Unsloth + LoRA
+* LoRA config: r=1024, alpha=1024, dropout=0.0, full attention + FFN adaptation
+* Quantization: 4-bit (bnb) for training; final model is highly memory-efficient
+* Total steps: 18,014 (1 epoch)
+* Batch size: 1 × 4 (grad accum)
+* GPU: A100 40GB (max 55% VRAM used)
+
+
+<div style="margin-top: 20px;">
+<table style="border-collapse: collapse;">
+  <thead>
+    <tr>
+        <th style="border: 1px solid #ddd; padding: 8px; text-align: left;">Step</th>
+        <th style="border: 1px solid #ddd; padding: 8px; text-align: left;">Training Loss</th>
+        <th style="border: 1px solid #ddd; padding: 8px; text-align: left;">Validation Loss</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+        <td style="border: 1px solid #ddd; padding: 8px;">5,000</td>
+        <td style="border: 1px solid #ddd; padding: 8px;">3.9496</td>
+        <td style="border: 1px solid #ddd; padding: 8px;">3.8790</td>
+    </tr>
+    <tr>
+        <td style="border: 1px solid #ddd; padding: 8px;">10,000</td>
+        <td style="border: 1px solid #ddd; padding: 8px;">3.8863</td>
+        <td style="border: 1px solid #ddd; padding: 8px;">3.79497</td>
+    </tr>
+    <tr>
+        <td style="border: 1px solid #ddd; padding: 8px;">15,000</td>
+        <td style="border: 1px solid #ddd; padding: 8px;">3.8544</td>
+        <td style="border: 1px solid #ddd; padding: 8px;">3.75323</td>
+    </tr>
+  </tbody>
+</table>
+</div>
+
+### Dataset Summary
+
+* Sources:
+    * ✅ Manually aligned YouTube transcriptions (aka Random)
+    * ✅ Synthetic voice generation from Orpheus TTS
+    * ✅ Parallel text-audio pairs for African-English, Igbo, Yoruba, Hausa
+* Total Hours: 300+ (multi-accent)
+* Key Speakers: 45+ unique voices (see speaker distribution chart below)
+
+![image/png](https://huggingface.co/hypaai/Hypa_Orpheus-3b-0.1-ft-unsloth-bnb-4bit/resolve/main/assets/stats.png)
+
+We plan to open-source the full dataset shortly similar to the [Hypa_Fleurs](https://huggingface.co/datasets/hypaai/Hypa_Fleurs) initiative.
+
+---
+
+## Licensing and Citation
+
+This model is released under an [Open Source License](./LICENSE) (apache-2.0). Please refer to the LICENSE file for full details.
+
+When using this model in your work, please cite both this model as well as the base [`canopylabs/orpheus-3b-0.1-ft`](https://huggingface.co/canopylabs/orpheus-3b-0.1-ft) model as follows:
+
+```bibtex
+@misc{canopylabsorpheus,
+  title={Orpheus-3b-0.1-ft: A Multilingual Text-to-Speech Model},
+  author={Canopy Labs},
+  year={2025},
+  publisher={Hugging Face},
+  howpublished={\url{https://huggingface.co/canopylabs/orpheus-3b-0.1-ft}},
+  note={Fine-tuned version of Orpheus for expressive TTS}
+}
+
+@misc{hypaorpheus4bit,
+  title={Hypa_Orpheus-3b-0.1-ft (LoRA-4bit)},
+  author={Hypa AI},
+  year={2025},
+  note={Fine-tuned Orpheus TTS on African languages},
+  url={https://huggingface.co/hypaai/Hypa_Orpheus-3b-0.1-ft-unsloth-bnb-4bit}
+}
+```
+
+---
+
+## Acknowledgements
+
+- **Canopy Labs Team:** For creating the foundational model and opensourcing it.
+- **AfroVoices Experts:** For their translation expertise and high-quality datasets.
+- **Community Support:** We thank all supporters, contributors, and users.
+
+---
+
+## Contact and Contributions
+
+For any questions, issues, or contributions, please open an issue in this repository or contact [[email protected]](mailto:[email protected]). Contributions are welcome!
+
+---
+
+## Closing Remarks
+
+By making Hypa_Orpheus available, we hope to empower research and development in multilingual speech technologies for African languages.
+
+Hypa AI remains steadfast in its mission to pioneer intelligent solutions that are not just technologically advanced but are also culturally aware, ensuring that the future of AI is as diverse and inclusive as the world it serves.
+
+AfroVoices, a subsidiary of Hypa AI, is dedicated to amplifying African voices, languages, and cultures in the intelligence age. Focused on bridging the digital representation gap, AfroVoices curates datasets and resources for African languages, promoting inclusivity and cultural appreciation in AI technologies. Their mission goes beyond technological innovation, aiming to celebrate the richness of African linguistic diversity on a global stage.
+
+---
+
+## Usage
+
+### Unsloth Inference
+
+Download the nedded packages.
+
+```python
+%%capture
+import os
+if "COLAB_" not in "".join(os.environ.keys()):
+    !pip install unsloth
+else:
+    # Do this only in Colab notebooks! Otherwise use pip install unsloth
+    !pip install --no-deps bitsandbytes accelerate xformers==0.0.29.post3 peft trl==0.15.2 triton cut_cross_entropy unsloth_zoo
+    !pip install sentencepiece protobuf datasets huggingface_hub hf_transfer
+    !pip install --no-deps unsloth
+!pip install snac
+```
+
+Download the models (both the SNAC encoder/decoder as well as our finetuned Hypa_Orpheus).
+
+```python
+import torch
+from snac import SNAC
+from unsloth import FastLanguageModel
+
+dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
+load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.
+
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name = "hypaai/Hypa_Orpheus-3b-0.1-ft-unsloth-merged_16bit",
+    max_seq_length= 2048, # Choose any for long context!
+    dtype = dtype,
+    load_in_4bit = load_in_4bit,
+    #token = "hf_...", # use one if using gated models like meta-llama/Llama-2-7b-hf
+)
+
+snac_model = SNAC.from_pretrained("hubertsiuzdak/snac_24khz")
+snac_model = snac_model.to("cuda")
+```
+
+Create your text prompt, select the voice, and pass through the Model.
+
+```python
+prompts = [
+    """Mo nífẹ̀ẹ́sí láti ṣe Ph.D sùgbọ́n mi ò ì tíì pinnu ẹ̀ka tí màá ṣe. Àwọn anfaani tí óń dé oríṣiríṣi àwọn olùgbọ́ káàkiri àgbáyé wo ni mo ní""",
+]
+chosen_voice = "Eniola" # None for single-speaker
+
+
+FastLanguageModel.for_inference(model) # Enable native 2x faster inference
+snac_model.to("cpu")# Moving snac_model cuda to cpu
+
+prompts_ = [(f"{chosen_voice}: " + p) if chosen_voice else p for p in prompts]
+
+all_input_ids = []
+
+for prompt in prompts_:
+  input_ids = tokenizer(prompt, return_tensors="pt").input_ids
+  all_input_ids.append(input_ids)
+
+start_token = torch.tensor([[ 128259]], dtype=torch.int64) # Start of human
+end_tokens = torch.tensor([[128009, 128260]], dtype=torch.int64) # End of text, End of human
+
+all_modified_input_ids = []
+for input_ids in all_input_ids:
+  modified_input_ids = torch.cat([start_token, input_ids, end_tokens], dim=1) # SOH SOT Text EOT EOH
+  all_modified_input_ids.append(modified_input_ids)
+
+all_padded_tensors = []
+all_attention_masks = []
+max_length = max([modified_input_ids.shape[1] for modified_input_ids in all_modified_input_ids])
+for modified_input_ids in all_modified_input_ids:
+  padding = max_length - modified_input_ids.shape[1]
+  padded_tensor = torch.cat([torch.full((1, padding), 128263, dtype=torch.int64), modified_input_ids], dim=1)
+  attention_mask = torch.cat([torch.zeros((1, padding), dtype=torch.int64), torch.ones((1, modified_input_ids.shape[1]), dtype=torch.int64)], dim=1)
+  all_padded_tensors.append(padded_tensor)
+  all_attention_masks.append(attention_mask)
+
+all_padded_tensors = torch.cat(all_padded_tensors, dim=0)
+all_attention_masks = torch.cat(all_attention_masks, dim=0)
+
+input_ids = all_padded_tensors.to("cuda")
+attention_mask = all_attention_masks.to("cuda")
+generated_ids = model.generate(
+      input_ids=input_ids,
+      attention_mask=attention_mask,
+      max_new_tokens=1200,
+      do_sample=True,
+      temperature=0.6,
+      top_p=0.95,
+      repetition_penalty=1.1,
+      num_return_sequences=1,
+      eos_token_id=128258,
+     use_cache = True
+  )
+token_to_find = 128257
+token_to_remove = 128258
+
+token_indices = (generated_ids == token_to_find).nonzero(as_tuple=True)
+
+if len(token_indices[1]) > 0:
+    last_occurrence_idx = token_indices[1][-1].item()
+    cropped_tensor = generated_ids[:, last_occurrence_idx+1:]
+else:
+    cropped_tensor = generated_ids
+
+mask = cropped_tensor != token_to_remove
+
+processed_rows = []
+
+for row in cropped_tensor:
+    masked_row = row[row != token_to_remove]
+    processed_rows.append(masked_row)
+
+code_lists = []
+
+for row in processed_rows:
+    row_length = row.size(0)
+    new_length = (row_length // 7) * 7
+    trimmed_row = row[:new_length]
+    trimmed_row = [t - 128266 for t in trimmed_row]
+    code_lists.append(trimmed_row)
+
+
+def redistribute_codes(code_list):
+  layer_1 = []
+  layer_2 = []
+  layer_3 = []
+  for i in range((len(code_list)+1)//7):
+    layer_1.append(code_list[7*i])
+    layer_2.append(code_list[7*i+1]-4096)
+    layer_3.append(code_list[7*i+2]-(2*4096))
+    layer_3.append(code_list[7*i+3]-(3*4096))
+    layer_2.append(code_list[7*i+4]-(4*4096))
+    layer_3.append(code_list[7*i+5]-(5*4096))
+    layer_3.append(code_list[7*i+6]-(6*4096))
+  codes = [torch.tensor(layer_1).unsqueeze(0),
+         torch.tensor(layer_2).unsqueeze(0),
+         torch.tensor(layer_3).unsqueeze(0)]
+
+  # codes = [c.to("cuda") for c in codes]
+  audio_hat = snac_model.decode(codes)
+  return audio_hat
+
+my_samples = []
+for code_list in code_lists:
+  samples = redistribute_codes(code_list)
+  my_samples.append(samples)
+from IPython.display import display, Audio
+if len(prompts) != len(my_samples):
+  raise Exception("Number of prompts and samples do not match")
+else:
+  for i in range(len(my_samples)):
+    print(prompts[i])
+    samples = my_samples[i]
+    display(Audio(samples.detach().squeeze().to("cpu").numpy(), rate=24000))
+# Clean up to save RAM
+del my_samples,samples
+```
+
+### Standard Inference
+
+Download the nedded packages.
+
+```python
+%%capture
+!pip install snac ipywebrtc
+```
+
+Download the Models (SNAC & Hypa_Orpheus)
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, Trainer, TrainingArguments, AutoTokenizer
+from snac import SNAC
+
+# Loads the pre-trained SNAC model and moves it to the CPU.
+snac_model = SNAC.from_pretrained("hubertsiuzdak/snac_24khz")
+snac_model = snac_model #.to("cpu")
+
+print("We have loaded the Encoder/Decoder model to the cpu, to use vram - use the gpu for faster inference")
+
+# Loading the Orpheus Model and Tokenizer, moving the model to the GPU for faster inference
+model_name = "hypaai/Hypa_Orpheus-3b-0.1-ft-unsloth-merged_16bit"
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16)
+model.cuda()
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+```
+
+Create Prompt(s) and Select Voice & Emotions as needed.
+
+```python
+# List of supported voices in Orpheus-TTS
+voices = [
+    "Eniola", "tara",   # Female, conversational, clear
+    "Moyo", "leah",     # Female, warm, gentle
+    "Gift", "jess",     # Female, energetic, youthful
+    "Prince", "leo",    # Male, authoritative, deep
+    "Emmanuel", "dan",   # Male, friendly, casual
+    "Cynthia", "mia",    # Female, professional, articulate
+    "Kolade", "zac",    # Male, enthusiastic, dynamic
+    "Lovelyn", "zoe"     # Female, calm, soothing
+]
+
+# List of supported emotion tags in Orpheus-TTS
+emotions = [
+    "<laugh>",    # Laughter
+    "<chuckle>",  # Soft chuckle
+    "<sigh>",     # Sighing
+    "<cough>",    # Coughing
+    "<sniffle>",  # Sniffling
+    "<groan>",    # Groaning
+    "<yawn>",     # Yawning
+    "<gasp>"      # Gasping
+]
+
+# Creating Prompts
+prompts = [
+    "Hey there my name is Eniola 9000,  and I'm a speech generation model that can sound like a person.",
+    # "I've also been taught to understand and produce paralinguistic things like sighing, or chuckling, or yawning!",
+    # "I live in San Francisco, and have, uhm let's see, 3 billion 7 hundred ... well, lets just say a lot of parameters.",
+]
+
+chosen_voice = "Eniola"  # "tara" # see github for other voices
+prompts = [f"{chosen_voice}: " + p for p in prompts] # Creating the prompts (as a batch)
+print(prompts)
+```
+
+Tokenize prompt(s) into inputIDs, pad, and create attention masks.
+
+```python
+# Tokenizing each prompt into input IDs.
+all_input_ids = []
+for prompt in prompts:
+  input_ids = tokenizer(prompt, return_tensors="pt").input_ids
+  all_input_ids.append(input_ids)
+
+# Adds special tokens to mark the beginning and end of each prompt
+start_token = torch.tensor([[128259]], dtype=torch.int64) # Start of human
+end_tokens = torch.tensor([[128009, 128260]], dtype=torch.int64) # End of text, End of human
+
+all_modified_input_ids = []
+for input_ids in all_input_ids:
+  modified_input_ids = torch.cat([start_token, input_ids, end_tokens], dim=1) # SOH SOT Text EOT EOH
+  all_modified_input_ids.append(modified_input_ids)
+
+# Padding All sequences to same length and creating corresponding attention masks
+all_padded_tensors = []
+all_attention_masks = []
+max_length = max([modified_input_ids.shape[1] for modified_input_ids in all_modified_input_ids])
+for modified_input_ids in all_modified_input_ids:
+  padding = max_length - modified_input_ids.shape[1]
+  # Left Padding
+  padded_tensor = torch.cat([torch.full((1, padding), 128263, dtype=torch.int64), modified_input_ids], dim=1)
+  attention_mask = torch.cat([torch.zeros((1, padding), dtype=torch.int64), torch.ones((1, modified_input_ids.shape[1]), dtype=torch.int64)], dim=1)
+  all_padded_tensors.append(padded_tensor)
+  all_attention_masks.append(attention_mask)
+
+all_padded_tensors = torch.cat(all_padded_tensors, dim=0)
+all_attention_masks = torch.cat(all_attention_masks, dim=0)
+
+# Moving all padded sequences to GPU for Faster computation
+input_ids = all_padded_tensors.to("cuda")
+attention_mask = all_attention_masks.to("cuda")
+```
+
+Generate Output Tokens from the  and Parse output tokens as speech
+
+```python
+print("*** Model.generate is slow - see vllm implementation on github for realtime streaming and inference")
+print("*** Increase/decrease inference params for more expressive less stable generations")
+
+# Generating Output Tokens
+with torch.no_grad():
+  generated_ids = model.generate(
+      input_ids=input_ids,
+      attention_mask=attention_mask,
+      max_new_tokens=1200,
+      do_sample=True,
+      temperature=0.6,
+      top_p=0.95,
+      repetition_penalty=1.1,
+      num_return_sequences=1,
+      eos_token_id=128258,
+  )
+
+# Processing Generated Tokens (Parse Output as speech)
+token_to_find = 128257 # Start of Audio token (relevant output)
+token_to_remove = 128258 # End/ Terminal Token (End of Audio/ relevant output)
+
+token_indices = (generated_ids == token_to_find).nonzero(as_tuple=True)
+print(token_indices)
+
+# Slices the tensor to exclude unwanted tokens.
+if len(token_indices[1]) > 0:
+    last_occurrence_idx = token_indices[1][-1].item()
+    cropped_tensor = generated_ids[:, last_occurrence_idx+1:]
+else:
+    cropped_tensor = generated_ids
+
+# mask = cropped_tensor != token_to_remove
+
+# Storing the cleaned-up token sequences#
+processed_rows = []
+for row in cropped_tensor:
+    masked_row = row[row != token_to_remove]
+    processed_rows.append(masked_row)
+
+# Preparing (Audio Codes) the token sequences for audio decoding by trimming and adjusting token values.
+code_lists = []
+for row in processed_rows:
+    row_length = row.size(0) #  Determines the length of the token sequence.
+    new_length = (row_length // 7) * 7 # Ensures the sequence length is a multiple of 7, as required by the decoder.
+    trimmed_row = row[:new_length]
+    trimmed_row = [t - 128266 for t in trimmed_row] # Adjusts token values to match the expected input range for the decoder.
+    code_lists.append(trimmed_row)
+```
+
+Decode Outputs with SNAC Decoder
+
+```python
+# Processes the token sequences into the format expected by the SNAC decoder:
+def redistribute_codes(code_list):
+  """ Reorganizes the flattened token list into three separate layers, adjusting each token's value to align with the decoder's expectations"""
+  layer_1 = [] # Coarsest layer
+  layer_2 = [] # Intermediate layer
+  layer_3 = [] # Finest layer
+
+  num_groups = (len(code_list) + 1) // 7 #Calculate the number of complete 7-token groups in the code_list
+  for i in range(num_groups):
+    idx = 7 * i # starting index for the current group
+    # Layer 1 receives the first token of the group
+    layer_1.append(code_list[idx])
+
+    # Layer 2 receives the second token, adjusted by subtracting 4096
+    layer_2.append(code_list[idx + 1] - 4096)
+
+    # Layer 3 receives the third and fourth tokens, adjusted by subtracting 8192 and 12288 respectively
+    layer_3.append(code_list[idx+2]-(2*4096))
+    layer_3.append(code_list[idx+3]-(3*4096))
+
+    # Layer 2 receives the fifth token, adjusted by subtracting 16384
+    layer_2.append(code_list[idx+4]-(4*4096))
+
+    # Layer 3 receives the sixth and seventh tokens, adjusted by subtracting 20480 and 24576 respectively
+    layer_3.append(code_list[idx+5]-(5*4096))
+    layer_3.append(code_list[idx+6]-(6*4096))
+
+  codes = [
+        torch.tensor(layer_1).unsqueeze(0), # Shape: (1, len(layer_1))
+        torch.tensor(layer_2).unsqueeze(0), # Shape: (1, len(layer_2))
+        torch.tensor(layer_3).unsqueeze(0) # Shape: (1, len(layer_3))
+        ]  # Convert the lists to PyTorch tensors and add a batch dimension
+  audio_hat = snac_model.decode(codes) # Decode the structured codes into an audio waveform using the SNAC model
+  return audio_hat
+
+my_samples = []
+for code_list in code_lists:
+  samples = redistribute_codes(code_list) # Generates audio samples from the processed token sequences
+  my_samples.append(samples)
+
+# Display Audio
+from IPython.display import display, Audio
+
+if len(prompts) != len(my_samples):
+  raise Exception("Number of prompts and samples do not match")
+else:
+  for i in range(len(my_samples)):
+    print(prompts[i])
+    samples = my_samples[i]
+    display(Audio(samples.detach().squeeze().to("cpu").numpy(), rate=24000))
+```
+
+- **Repository:** [N/A]
+- **Paper:** [N/A]
+- **Demo:** [N/A]
+
+This llama based model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

assets/Emmanuel_English.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f7ed6302c725516d040d03e03331d2a4777026037e97099a337f20319880034
+size 487468

assets/Emmanuel_Hausa.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29da60c6dffcdfa4fe402489bdb3040bc3ce0085bbae0f7e9b52d1b9d1a2b000
+size 688172

assets/Eniola_English.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edd3e58ea65a92bf691db4ca20bd68cc5fc5e6e5cef715cc798279b978f3e5aa
+size 344108

assets/Eniola_Hausa.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40dd9ee114f53b1bdb3f32d3be21476fcd758de376d4d4252e45d00a5ccfa8ba
+size 548908

assets/Eniola_Igbo.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a05aabf5f577c4b1703a10d4999a1872068d16e6013492d28bf2d83950c856a6
+size 483372

assets/Eniola_Yoruba.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c97b3527e108805280eddde2be8c090eeb8507917db334c645933567fb3b155
+size 479276

assets/Lovelyn_English.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40a2640afa40eb2f0aa6a8db18143a070f17986bd8ac7e70a099ec3f558d4a01
+size 348204

assets/Lovelyn_Igbo.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc38cc3a3e73c3bf9bbf207f68e8983e9f93da5f57f14ed8e8aea4bc997e47d8
+size 434220

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128004,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "unsloth_fixed": true,
+  "unsloth_version": "2025.3.19",
+  "use_cache": true,
+  "vocab_size": 156940
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128009,
+  "max_length": 131072,
+  "pad_token_id": 128004,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.51.3"
+}

handler.py

@@ -0,0 +1,302 @@
+"""
+# Orpheus TTS Handler - Explanation & Deployment Guide
+
+This guide explains how to properly deploy the Orpheus TTS model with the custom 
+handler on Hugging Face Inference Endpoints.
+
+## The Problem
+
+Based on the error messages you're seeing:
+1. Connection is working (you get responses) 
+2. But responses contain text rather than audio data
+3. The response format is the standard HF format: [{"generated_text": "..."}]
+
+This indicates that your endpoint is running the standard text generation handler
+rather than the custom audio generation handler you've defined.
+
+## Step 1: Properly package your handler
+
+Create a `handler.py` file with your custom handler code:
+"""
+
+import os
+import torch
+import numpy as np
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from snac import SNAC
+import logging
+
+# Set up logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+class EndpointHandler:
+    def __init__(self, path=""):
+        logger.info("Initializing Orpheus TTS handler")
+        # Load the Orpheus model and tokenizer
+        self.model_name = "hypaai/Hypa_Orpheus-3b-0.1-ft-unsloth-merged_16bit"
+        self.model = AutoModelForCausalLM.from_pretrained(
+            self.model_name, 
+            torch_dtype=torch.bfloat16
+        )
+        
+        # Move model to GPU if available
+        self.device = "cuda" if torch.cuda.is_available() else "cpu"
+        self.model.to(self.device)
+        logger.info(f"Model loaded on {self.device}")
+        
+        # Load tokenizer
+        self.tokenizer = AutoTokenizer.from_pretrained(self.model_name)
+        logger.info("Tokenizer loaded")
+        
+        # Load SNAC model for audio decoding
+        try:
+            self.snac_model = SNAC.from_pretrained("hubertsiuzdak/snac_24khz")
+            self.snac_model.to(self.device)
+            logger.info("SNAC model loaded")
+        except Exception as e:
+            logger.error(f"Error loading SNAC: {str(e)}")
+            raise
+        
+        # Special tokens
+        self.start_token = torch.tensor([[128259]], dtype=torch.int64)  # Start of human
+        self.end_tokens = torch.tensor([[128009, 128260]], dtype=torch.int64)  # End of text, End of human
+        self.padding_token = 128263
+        self.start_audio_token = 128257  # Start of Audio token
+        self.end_audio_token = 128258  # End of Audio token
+
+        self._warmed_up = False
+        
+        logger.info("Handler initialization complete")
+        
+    def preprocess(self, data):
+        """
+        Preprocess input data before inference
+        """
+        logger.info(f"Preprocessing data: {type(data)}")
+        
+        # Handle health check
+        if data == "ping" or (isinstance(data, dict) and data.get("inputs") == "ping"):
+            logger.info("Health check detected")
+            return {"health_check": True}
+            
+        # HF Inference API format: 'inputs' is the text, 'parameters' contains the config
+        if isinstance(data, dict) and "inputs" in data:
+            # Standard HF format
+            text = data["inputs"]
+            parameters = data.get("parameters", {})
+        else:
+            # Direct access (fallback)
+            text = data
+            parameters = {}
+        
+        # Extract parameters from request
+        voice = parameters.get("voice", "tara")
+        temperature = float(parameters.get("temperature", 0.6))
+        top_p = float(parameters.get("top_p", 0.95))
+        max_new_tokens = int(parameters.get("max_new_tokens", 1200))
+        repetition_penalty = float(parameters.get("repetition_penalty", 1.1))
+        
+        # Format prompt with voice
+        prompt = f"{voice}: {text}"
+        logger.info(f"Formatted prompt with voice {voice}")
+        
+        # Tokenize
+        input_ids = self.tokenizer(prompt, return_tensors="pt").input_ids
+        
+        # Add special tokens
+        modified_input_ids = torch.cat([self.start_token, input_ids, self.end_tokens], dim=1)
+        
+        # No need for padding as we're processing a single sequence
+        input_ids = modified_input_ids.to(self.device)
+        attention_mask = torch.ones_like(input_ids)
+        
+        return {
+            "input_ids": input_ids,
+            "attention_mask": attention_mask,
+            "temperature": temperature,
+            "top_p": top_p,
+            "max_new_tokens": max_new_tokens,
+            "repetition_penalty": repetition_penalty,
+            "health_check": False
+        }
+    
+    def inference(self, inputs):
+        """
+        Run model inference on the preprocessed inputs
+        """
+        # Handle health check
+        if inputs.get("health_check", False):
+            return {"status": "ok"}
+            
+        # Extract parameters
+        input_ids = inputs["input_ids"]
+        attention_mask = inputs["attention_mask"]
+        temperature = inputs["temperature"]
+        top_p = inputs["top_p"]
+        max_new_tokens = inputs["max_new_tokens"]
+        repetition_penalty = inputs["repetition_penalty"]
+        
+        logger.info(f"Running inference with max_new_tokens={max_new_tokens}")
+        
+        # Generate output tokens
+        with torch.no_grad():
+            generated_ids = self.model.generate(
+                input_ids=input_ids,
+                attention_mask=attention_mask,
+                max_new_tokens=max_new_tokens,
+                do_sample=True,
+                temperature=temperature,
+                top_p=top_p,
+                repetition_penalty=repetition_penalty,
+                num_return_sequences=1,
+                eos_token_id=self.end_audio_token,
+            )
+        
+        logger.info(f"Generation complete, output shape: {generated_ids.shape}")
+        return generated_ids
+    
+    def postprocess(self, generated_ids):
+        """
+        Process generated tokens into audio
+        """
+        # Handle health check response
+        if isinstance(generated_ids, dict) and "status" in generated_ids:
+            return generated_ids
+            
+        logger.info("Postprocessing generated tokens")
+        
+        # Find Start of Audio token
+        token_indices = (generated_ids == self.start_audio_token).nonzero(as_tuple=True)
+        
+        if len(token_indices[1]) > 0:
+            last_occurrence_idx = token_indices[1][-1].item()
+            cropped_tensor = generated_ids[:, last_occurrence_idx+1:]
+            logger.info(f"Found start audio token at position {last_occurrence_idx}")
+        else:
+            cropped_tensor = generated_ids
+            logger.warning("No start audio token found")
+            
+        # Remove End of Audio tokens
+        processed_rows = []
+        for row in cropped_tensor:
+            masked_row = row[row != self.end_audio_token]
+            processed_rows.append(masked_row)
+            
+        # Prepare audio codes
+        code_lists = []
+        for row in processed_rows:
+            row_length = row.size(0)
+            # Ensure length is multiple of 7 for SNAC
+            new_length = (row_length // 7) * 7
+            trimmed_row = row[:new_length]
+            trimmed_row = [t.item() - 128266 for t in trimmed_row]  # Adjust token values
+            code_lists.append(trimmed_row)
+            
+        # Generate audio from codes
+        audio_samples = []
+        for code_list in code_lists:
+            logger.info(f"Processing code list of length {len(code_list)}")
+            if len(code_list) > 0:
+                audio = self.redistribute_codes(code_list)
+                audio_samples.append(audio)
+            else:
+                logger.warning("Empty code list, no audio to generate")
+                
+        if not audio_samples:
+            logger.error("No audio samples generated")
+            return {"error": "No audio samples generated"}
+            
+        # Return first (and only) audio sample
+        audio_sample = audio_samples[0].detach().squeeze().cpu().numpy()
+        
+        # Convert to base64 for transmission
+        import base64
+        import io
+        import wave
+        
+        # Convert float32 array to int16 for WAV format
+        audio_int16 = (audio_sample * 32767).astype(np.int16)
+        
+        # Create WAV in memory
+        with io.BytesIO() as wav_io:
+            with wave.open(wav_io, 'wb') as wav_file:
+                wav_file.setnchannels(1)  # Mono
+                wav_file.setsampwidth(2)  # 16-bit
+                wav_file.setframerate(24000)  # 24kHz
+                wav_file.writeframes(audio_int16.tobytes())
+            wav_data = wav_io.getvalue()
+        
+        # Encode as base64
+        audio_b64 = base64.b64encode(wav_data).decode('utf-8')
+        logger.info(f"Audio encoded as base64, length: {len(audio_b64)}")
+        
+        return {
+            "audio_sample": audio_sample,
+            "audio_b64": audio_b64,
+            "sample_rate": 24000
+        }
+    
+    def redistribute_codes(self, code_list):
+        """
+        Reorganize tokens for SNAC decoding
+        """
+        layer_1 = []  # Coarsest layer
+        layer_2 = []  # Intermediate layer
+        layer_3 = []  # Finest layer
+        
+        num_groups = len(code_list) // 7
+        for i in range(num_groups):
+            idx = 7 * i
+            layer_1.append(code_list[idx])
+            layer_2.append(code_list[idx + 1] - 4096)
+            layer_3.append(code_list[idx + 2] - (2 * 4096))
+            layer_3.append(code_list[idx + 3] - (3 * 4096))
+            layer_2.append(code_list[idx + 4] - (4 * 4096))
+            layer_3.append(code_list[idx + 5] - (5 * 4096))
+            layer_3.append(code_list[idx + 6] - (6 * 4096))
+        
+        codes = [
+            torch.tensor(layer_1).unsqueeze(0).to(self.device),
+            torch.tensor(layer_2).unsqueeze(0).to(self.device),
+            torch.tensor(layer_3).unsqueeze(0).to(self.device)
+        ]
+        
+        # Decode audio
+        audio_hat = self.snac_model.decode(codes)
+        return audio_hat
+    
+    def __call__(self, data):
+        """
+        Main entry point for the handler
+        """
+        # Run warmup only once, the first time __call__ is triggered
+        if not self._warmed_up:
+            self._warmup()
+        
+        try:
+            logger.info(f"Received request: {type(data)}")
+            
+            # Check if we need to handle the health check route
+            if data == "ping" or (isinstance(data, dict) and data.get("inputs") == "ping"):
+                logger.info("Processing health check request")
+                return {"status": "ok"}
+                
+            preprocessed_inputs = self.preprocess(data)
+            model_outputs = self.inference(preprocessed_inputs)
+            response = self.postprocess(model_outputs)
+            return response
+        except Exception as e:
+            logger.error(f"Error processing request: {str(e)}")
+            import traceback
+            logger.error(traceback.format_exc())
+            return {"error": str(e)}
+
+    def _warmup(self):
+        try:
+            dummy_prompt = "tara: Hello"
+            input_ids = self.tokenizer(dummy_prompt, return_tensors="pt").input_ids.to(self.device)
+            _ = self.model.generate(input_ids=input_ids, max_new_tokens=5)
+            self._warmed_up = True
+        except Exception as e:
+            print(f"[WARMUP ERROR] {str(e)}")

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8213aa17429d0aa9e5efa37fdcb305683aec81f781d44397e4fbf3fb3e361188
+size 4991037968

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:151d8b600614a200e322528b791155a75ae6f703a2a7ffb269e974e4cdb1c219
+size 1610725592

model.safetensors.index.json

@@ -0,0 +1,261 @@
+{
+  "metadata": {
+    "total_size": 6601734144
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

requirements.txt

@@ -0,0 +1,5 @@
+torch>=2.0.0
+transformers>=4.30.0
+snac>=0.1.0
+numpy>=1.20.0
+protobuf

special_tokens_map.json

@@ -0,0 +1,26 @@
+{
+  "additional_special_tokens": [
+    "<|audio|>"
+  ],
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc3fecb199b4170636dbfab986d25f628157268d37b861f9cadaca60b1353bce
+size 22849547