Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,53 @@
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
 *.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
 *.ftz filter=lfs diff=lfs merge=lfs -text
 *.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
 *.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
 *.xz filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+
+g2p/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+
+g2p/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+
+g2p/tokenizer.json filter=lfs diff=lfs merge=lfs -text

.mv

@@ -0,0 +1 @@
+Revision:master,CreatedAt:1743818252

README.md

@@ -1,6 +1,161 @@
 ---
+language:
+- en
+- zh
 license: apache-2.0
+pipeline_tag: text-to-speech
 ---
-# MegaTTS 3 but with support for voice cloning
 
-All credits to: https://modelscope.cn/models/ACoderPassBy/MegaTTS-SFT
+非官方实现版本，包括全量参数。
+
+
+# Model Description
+This is a ModelScope model card for MegaTTS 3 👋
+
+-   Paper: [MegaTTS 3: Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesis](https://huggingface.co/papers/2502.18924)
+-   Project Page (Audio Samples): <https://sditdemo.github.io/sditdemo/>
+-   github: <https://github.com/bytedance/MegaTTS3>
+-   [Demo Video](https://github.com/user-attachments/assets/0174c111-f392-4376-a34b-0b5b8164aacc)
+
+
+## Installation
+
+```sh
+# Clone the repository
+git clone https://github.com/bytedance/MegaTTS3
+cd MegaTTS3
+```
+
+**Model Download**
+
+```sh
+modelscope download --model ACoderPassBy/MegaTTS-SFT --local_dir ./checkpoints
+```
+
+**Requirements (for Linux)**
+
+```sh
+# Create a python 3.10 conda env (you could also use virtualenv)
+conda create -n megatts3-env python=3.10
+conda activate megatts3-env
+pip install -r requirements.txt
+
+# Set the root directory
+export PYTHONPATH="/path/to/MegaTTS3:$PYTHONPATH"
+
+# [Optional] Set GPU
+export CUDA_VISIBLE_DEVICES=0
+
+# If you encounter bugs with pydantic in inference, you should check if the versions of pydantic and gradio are matched.
+# [Note] if you encounter bugs related with httpx, please check that whether your environmental variable "no_proxy" has patterns like "::"
+```
+
+**Requirements (for Windows)**
+
+```sh
+# [The Windows version is currently under testing]
+# Comment below dependence in requirements.txt:
+# # WeTextProcessing==1.0.4.1
+
+# Create a python 3.10 conda env (you could also use virtualenv)
+conda create -n megatts3-env python=3.10
+conda activate megatts3-env
+pip install -r requirements.txt
+conda install -y -c conda-forge pynini==2.1.5
+pip install WeTextProcessing==1.0.3
+
+# [Optional] If you want GPU inference, you may need to install specific version of PyTorch for your GPU from https://pytorch.org/.
+pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu126
+
+# [Note] if you encounter bugs related with `ffprobe` or `ffmpeg`, you can install it through `conda install -c conda-forge ffmpeg`
+
+# Set environment variable for root directory
+set PYTHONPATH="C:\path\to\MegaTTS3;%PYTHONPATH%" # Windows
+$env:PYTHONPATH="C:\path\to\MegaTTS3;%PYTHONPATH%" # Powershell on Windows
+conda env config vars set PYTHONPATH="C:\path\to\MegaTTS3;%PYTHONPATH%" # For conda users
+
+# [Optional] Set GPU
+set CUDA_VISIBLE_DEVICES=0 # Windows
+$env:CUDA_VISIBLE_DEVICES=0 # Powershell on Windows
+```
+
+**Requirements (for Docker)**
+
+```sh
+# [The Docker version is currently under testing]
+# ! You should download the pretrained checkpoint before running the following command
+docker build . -t megatts3:latest
+
+# For GPU inference
+docker run -it -p 7929:7929 --gpus all -e CUDA_VISIBLE_DEVICES=0 megatts3:latest
+# For CPU inference
+docker run -it -p 7929:7929  megatts3:latest
+
+# Visit http://0.0.0.0:7929/ for gradio.
+```
+
+> \[!TIP]
+> \[IMPORTANT]
+> 非官方版本
+
+## Inference
+
+**Command-Line Usage (Standard)**
+
+```bash
+# p_w (intelligibility weight), t_w (similarity weight). Typically, prompt with more noises requires higher p_w and t_w
+python tts/infer_cli.py --input_wav 'assets/Chinese_prompt.wav'  --input_text "另一边的桌上,一位读书人嗤之以鼻道,'佛子三藏,神子燕小鱼是什么样的人物,李家的那个李子夜如何与他们相提并论？'" --output_dir ./gen
+
+# As long as audio volume and pronunciation are appropriate, increasing --t_w within reasonable ranges (2.0~5.0)
+# will increase the generated speech's expressiveness and similarity (especially for some emotional cases).
+python tts/infer_cli.py --input_wav 'assets/English_prompt.wav' --input_text 'As his long promised tariff threat turned into reality this week, top human advisers began fielding a wave of calls from business leaders, particularly in the automotive sector, along with lawmakers who were sounding the alarm.' --output_dir ./gen --p_w 2.0 --t_w 3.0
+```
+
+**Command-Line Usage (for TTS with Accents)**
+
+```bash
+# When p_w (intelligibility weight) ≈ 1.0, the generated audio closely retains the speaker’s original accent. As p_w increases, it shifts toward standard pronunciation.
+# t_w (similarity weight) is typically set 0–3 points higher than p_w for optimal results.
+# Useful for accented TTS or solving the accent problems in cross-lingual TTS.
+python tts/infer_cli.py --input_wav 'assets/English_prompt.wav' --input_text '这是一条有口音的音频。' --output_dir ./gen --p_w 1.0 --t_w 3.0
+
+python tts/infer_cli.py --input_wav 'assets/English_prompt.wav' --input_text '这条音频的发音标准一些了吗？' --output_dir ./gen --p_w 2.5 --t_w 2.5
+```
+
+**Web UI Usage**
+
+```bash
+# We also support cpu inference, but it may take about 30 seconds (for 10 inference steps).
+python tts/gradio_api.py
+```
+
+## Security
+
+If you discover a potential security issue in this project, or think you may
+have discovered a security issue, we ask that you notify Bytedance Security via our [security center](https://security.bytedance.com/src) or [[email protected]]([email protected]).
+
+Please do **not** create a public issue.
+
+## License
+
+This project is licensed under the [Apache-2.0 License](LICENSE).
+
+## BibTeX Entry and Citation Info
+
+This repo contains forced-align version of `Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesis` and the WavVAE is mainly based on `Wavtokenizer: an efficient acoustic discrete codec tokenizer for audio language modeling`. Compared to the model described in paper, the repository includes additional models. These models not only enhance the stability and cloning capabilities of the algorithm but can also be independently utilized to serve a wider range of scenarios.
+
+```
+@article{jiang2025sparse,
+  title={Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesis},
+  author={Jiang, Ziyue and Ren, Yi and Li, Ruiqi and Ji, Shengpeng and Ye, Zhenhui and Zhang, Chen and Jionghao, Bai and Yang, Xiaoda and Zuo, Jialong and Zhang, Yu and others},
+  journal={arXiv preprint arXiv:2502.18924},
+  year={2025}
+}
+
+@article{ji2024wavtokenizer,
+  title={Wavtokenizer: an efficient acoustic discrete codec tokenizer for audio language modeling},
+  author={Ji, Shengpeng and Jiang, Ziyue and Wang, Wen and Chen, Yifu and Fang, Minghui and Zuo, Jialong and Yang, Qian and Cheng, Xize and Wang, Zehan and Li, Ruiqi and others},
+  journal={arXiv preprint arXiv:2408.16532},
+  year={2024}
+}
+```

aligner_lm/config.yaml

@@ -0,0 +1,151 @@
+acous_params:
+- - 480
+  - 1200
+  - 80
+- - 240
+  - 1200
+  - 160
+amp: true
+audio_num_mel_bins: 160
+audio_sample_rate: 24000
+base_config:
+- ./base_config.yaml
+c_spk_enc: 512
+char_dict_size: 15000
+conv_use_pos: false
+dec0_dilations:
+- 1
+- 2
+- 4
+- 1
+- 2
+- 4
+- 1
+dec0_kernel_size: 3
+dec_dilations:
+- 1
+- 2
+- 1
+- 2
+- 1
+dec_ffn_kernel_size: 9
+dec_kernel_size: 5
+dec_layers: 4
+dec_post_net_kernel: 3
+decoder_rnn_dim: 0
+decoder_type: conv
+dropout: 0.0
+dur_alpha: 1.0
+dur_context_enc: true
+dur_log: true
+dur_predictor_kernel: 3
+dur_predictor_layers: 2
+dur_use_char: true
+dur_use_spk: true
+enc_dec_norm: ln
+enc_dilations:
+- 1
+- 1
+- 1
+- 1
+enc_ffn_kernel_size: 5
+enc_kernel_size: 5
+enc_layers: 8
+enc_post_net_kernel: 3
+enc_pre_ln: true
+enc_prenet: true
+encoder_K: 8
+encoder_type: rel_fft
+endless_ds: true
+eval_max_batches: 0
+f0_max: 600
+f0_min: 60
+ffn_act: gelu
+ffn_hidden_size: 1024
+fft_size: 1200
+fg_spk_enc_hidden: 256
+fmax: 12000
+fmin: 0
+frames_multiple: 8
+hidden_size: 512
+hop_size: 240
+keep_c0_init: true
+lat_for_dur: false
+latent_dim: 16
+latent_size: 256
+layers_in_block: 2
+ling_label_dict_size:
+- 20
+- 4
+- 5
+- 2
+- 3
+- 3
+- 3
+- 6
+- 15
+ling_labels:
+- tone
+loud_norm: false
+mel_vmax: 0.5
+mel_vmin: -6
+min_frames: 50
+mix_melout_timbre: true
+mix_ph_timbre: false
+mixed_precision: bf16
+model_type: 1
+multistage: false
+no_text_enc: false
+num_ckpt_keep: 5
+num_heads: 2
+num_spk: 50000
+out_wav_norm: true
+pitch_extractor: reaper
+pitch_key: pitch
+pitch_type: frame
+precision: bf16
+ref_mel_bins: 160
+seed: 1234
+split_ref: true
+use_bert_input: false
+use_cfg: true
+use_char: true
+use_cur_global: false
+use_cur_global_dec: true
+use_dur_embed: true
+use_dur_mask_embed: true
+use_ema: false
+use_expand_ph: true
+use_finegrained_spk: false
+use_gt_dur: false
+use_gt_f0: false
+use_mix_spk_embed: false
+use_new_vae: false
+use_ph_level_f0: false
+use_ph_pos_embed: true
+use_pitch_embed: false
+use_pitch_embed_dec: false
+use_pitch_pred: true
+use_pos_embed: true
+use_qk_norm: true
+use_random_spk_embed: false
+use_seq_cfg: true
+use_spk_embed: false
+use_spk_enc: true
+use_spk_id: false
+use_uv: true
+use_vae: true
+use_vpcfm: true
+use_vqvae: true
+use_word_encoder: true
+use_word_input: false
+vae_dur_grad: 0.1
+vae_enc_hidden_size: 384
+vae_stride: 4
+vae_word_conder_layers: 0
+vq_stride: 8
+vqvae_start_steps: 0
+win_size: 1200
+word_dict_size: 10000
+z_channels: 64
+z_clamp: 2.0

aligner_lm/model_only_last.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a00f18ec36f8c1328ddab7a405c8e388790a1c14fdbdd07c546fcacaf5d19296
+size 218434266

config.json

@@ -0,0 +1,3 @@
+{
+  "name": this is a file used for counting downloads for models.
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-to-speech", "allow_remote": true}

diffusion_transformer/config.yaml

@@ -0,0 +1,148 @@
+acous_params:
+- - 480
+  - 1200
+  - 80
+- - 240
+  - 1200
+  - 160
+amp: true
+audio_num_mel_bins: 160
+audio_sample_rate: 24000
+base_config:
+- ./base_config.yaml
+c_spk_enc: 512
+char_dict_size: 15000
+conv_use_pos: false
+dec0_dilations:
+- 1
+- 2
+- 4
+- 1
+- 2
+- 4
+- 1
+dec0_kernel_size: 3
+dec_dilations:
+- 1
+- 2
+- 1
+- 2
+- 1
+dec_ffn_kernel_size: 9
+dec_inp_add_noise: false
+dec_kernel_size: 5
+dec_layers: 4
+dec_post_net_kernel: 3
+decoder_rnn_dim: 0
+decoder_type: conv
+dropout: 0.0
+ds_add_pitch_embed: false
+dur_alpha: 1.0
+dur_context_enc: true
+dur_log: true
+dur_predictor_kernel: 3
+dur_predictor_layers: 2
+dur_use_char: true
+dur_use_spk: true
+enc_dec_norm: ln
+enc_dilations:
+- 1
+- 1
+- 1
+- 1
+enc_ffn_kernel_size: 5
+enc_kernel_size: 5
+enc_layers: 8
+enc_post_net_kernel: 3
+enc_pre_ln: true
+enc_prenet: true
+encoder_K: 8
+encoder_type: rel_fft
+f0_max: 600
+f0_min: 60
+ffn_act: gelu
+ffn_hidden_size: 1024
+fft_size: 1200
+fg_spk_enc_hidden: 256
+fmax: 12000
+fmin: 0
+frames_multiple: 8
+gen_dir_name: ''
+hidden_size: 512
+hop_size: 240
+ignore_begin_end_sil: false
+keep_c0_init: true
+kl_min: 0
+kl_start_steps: 1
+latent_dim: 32
+latent_size: 256
+layers_in_block: 2
+ling_label_dict_size:
+- 20
+- 4
+- 5
+- 2
+- 3
+- 3
+- 3
+- 6
+- 15
+ling_labels:
+- tone
+loud_norm: false
+max_input_tokens: 1550
+mel_vmax: 0.5
+mel_vmin: -6
+min_frames: 50
+mix_melout_timbre: true
+mix_ph_timbre: false
+mixed_precision: bf16
+no_text_enc: false
+num_heads: 2
+out_wav_norm: true
+pad_frames: false
+
+precision: bf16
+seed: 1234
+use_bert_input: false
+use_cfg: true
+use_char: true
+use_cur_global: false
+use_cur_global_dec: true
+use_dit_1b: false
+use_dur_embed: true
+use_dur_mask_embed: true
+use_ema: false
+use_expand_ph: true
+use_finegrained_spk: false
+use_global_lat: false
+use_gt_dur: false
+use_gt_f0: false
+use_mix_spk_embed: false
+use_new_vae: false
+use_ph_level_f0: false
+use_ph_pos_embed: true
+use_pitch_embed: false
+use_pitch_embed_dec: false
+use_pitch_pred: true
+use_pos_embed: true
+use_qk_norm: true
+use_random_spk_embed: false
+use_seq_cfg: true
+use_spk_embed: false
+use_spk_enc: true
+use_spk_id: false
+use_uv: true
+use_vae: true
+use_vpcfm: true
+use_vqvae: true
+use_word_encoder: true
+use_word_input: false
+vae_dur_grad: 0.1
+vae_enc_hidden_size: 384
+vae_stride: 4
+vae_word_conder_layers: 0
+vq_stride: 8
+vqvae_start_steps: 0
+win_size: 1200
+word_dict_size: 10000

diffusion_transformer/model_only_last.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12233b95be177504551034390cf71aa748f0c66cbe2fd0ce433b9f9686122da9
+size 1836341777

duration_lm/config.yaml

@@ -0,0 +1,168 @@
+acous_params:
+- - 480
+  - 1200
+  - 80
+- - 240
+  - 1200
+  - 160
+amp: false
+audio_num_mel_bins: 160
+audio_sample_rate: 24000
+balance_sil: true
+c_spk_enc: 512
+char_dict_size: 15000
+conv_use_pos: false
+dec0_dilations:
+- 1
+- 2
+- 4
+- 1
+- 2
+- 4
+- 1
+dec0_kernel_size: 3
+dec_dilations:
+- 1
+- 2
+- 1
+- 2
+- 1
+dec_ffn_kernel_size: 9
+dec_hidden_size: 2048
+dec_inp_add_noise: false
+dec_kernel_size: 5
+dec_layers: 4
+dec_num_heads: 8
+dec_post_net_kernel: 3
+decoder_rnn_dim: 0
+decoder_type: conv
+dropout: 0.0
+ds_add_pitch_embed: false
+dur_alpha: 1.0
+dur_code_size: 128
+dur_context_enc: true
+dur_log: true
+dur_model_hidden_size: 512
+dur_model_layers: 8
+dur_model_type: ar_mse
+dur_predictor_kernel: 3
+dur_predictor_layers: 2
+dur_txt_hs: 512
+dur_use_char: true
+dur_use_spk: true
+enc_dec_norm: ln
+enc_dilations:
+- 1
+- 1
+- 1
+- 1
+enc_ffn_kernel_size: 3
+enc_hidden_size: 256
+enc_kernel_size: 5
+enc_layers: 4
+enc_post_net_kernel: 3
+enc_pre_ln: true
+enc_prenet: true
+encoder_K: 8
+encoder_type: rel_fft
+f0_max: 600
+f0_min: 60
+ffn_act: gelu
+ffn_hidden_size: 1024
+fft_size: 1200
+fg_spk_enc_hidden: 256
+flatten_dec: true
+fmax: 12000
+fmin: 0
+frames_multiple: 8
+hidden_size: 512
+hop_size: 240
+ignore_begin_end_sil: false
+lat_for_dur: false
+latent_size: 256
+layers_in_block: 2
+ling_label_dict_size:
+- 20
+- 4
+- 5
+- 2
+- 3
+- 3
+- 3
+- 6
+- 15
+ling_labels:
+- tone
+lm_num_layers: 24
+lm_use_enc: true
+loud_norm: false
+max_tokens: 6000
+mel_vmax: 0.5
+mel_vmin: -6
+min_frames: 0
+mix_melout_timbre: true
+mix_ph_timbre: false
+model_type: 1
+multistage: false
+no_text_enc: false
+num_heads: 2
+out_wav_norm: true
+pad_frames: false
+
+precision: fp16
+predict_pitch: false
+predictor_dropout: 0.0
+predictor_grad: 1.0
+predictor_hidden: -1
+predictor_kernel: 5
+predictor_layers: 5
+print_nan_grads: true
+ref_mel_bins: 160
+ref_size_max: 2000
+ref_size_min: 1000
+remove_sil: false
+shuffle_ref: false
+split_ref: true
+temperature: 0.8
+tone_percep_ckpt: ''
+train_spk_embed_only: false
+use_bert_input: false
+use_char: true
+use_cur_global: false
+use_cur_global_dec: true
+use_dur_embed: true
+use_dur_mask_embed: true
+use_finegrained_spk: false
+use_global_lat: false
+use_gpt: true
+use_gt_dur: false
+use_gt_f0: false
+use_mix_spk_embed: false
+use_new_vae: false
+use_ph_level_f0: false
+use_ph_pos_embed: true
+use_pitch_embed: false
+use_pitch_embed_dec: false
+use_pitch_pred: true
+use_pos_embed: false
+use_post_ln: false
+use_random_spk_embed: false
+use_rot_embed: true
+use_spk_embed: false
+use_spk_enc: false
+use_spk_id: false
+use_text_postnet: true
+use_uv: true
+use_vae: true
+use_vqvae: true
+use_word_encoder: true
+use_word_input: false
+vae_dur_grad: 0.1
+vae_enc_hidden_size: 384
+vae_word_conder_layers: 0
+vq_stride: 8
+w_nonsil: 10.0
+w_sil: 1.0
+word_dict_size: 10000
+z_channels: 64
+z_clamp: 2.0

duration_lm/model_only_last.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f21f4205c5d3ec4bef69716a85ca3d37f25c35b429bac500477a2085039b43f
+size 267955084

g2p/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "./checkpoints/Qwen2-0.5B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.3",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 168896
+}

g2p/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.48.3"
+}

g2p/latest

@@ -0,0 +1 @@
+global_step95500

g2p/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f9d70d454ee35d023a9a54552716a8ccf2411c967abc6a857160527046f62a2
+size 1018490136

g2p/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

g2p/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18bf578a236efa19e36ee7be04c327ba4abc23aed0213a31d3199a55ea7d2411
+size 14796960

wavvae/config.yaml

@@ -0,0 +1,232 @@
+acous_params:
+- - 480
+  - 1200
+  - 80
+- - 240
+  - 1200
+  - 160
+amp: false
+audio_num_mel_bins: 160
+audio_sample_rate: 24000
+c_spk_enc: 512
+char_dict_size: 15000
+conv_use_pos: false
+dec0_dilations:
+- 1
+- 2
+- 4
+- 1
+- 2
+- 4
+- 1
+dec0_kernel_size: 3
+dec_dilations:
+- 1
+- 2
+- 1
+- 2
+- 1
+dec_ffn_kernel_size: 9
+dec_inp_add_noise: false
+dec_kernel_size: 5
+dec_layers: 4
+dec_post_net_kernel: 3
+decoder_rnn_dim: 0
+decoder_type: conv
+dropout: 0.0
+ds_add_pitch_embed: false
+dur_alpha: 1.0
+dur_context_enc: true
+dur_log: true
+dur_predictor_kernel: 3
+dur_predictor_layers: 2
+dur_use_char: true
+dur_use_spk: true
+enc_dec_norm: ln
+enc_dilations:
+- 1
+- 1
+- 1
+- 1
+enc_ffn_kernel_size: 5
+enc_kernel_size: 5
+enc_layers: 8
+enc_post_net_kernel: 3
+enc_pre_ln: true
+enc_prenet: true
+encoder_K: 8
+encoder_type: rel_fft
+f0_max: 600
+f0_min: 60
+ffn_act: gelu
+ffn_hidden_size: 1024
+fft_size: 1200
+fg_spk_enc_hidden: 256
+fmax: 12000
+fmin: 0
+frames_multiple: 8
+hidden_size: 512
+hop_size: 240
+ignore_begin_end_sil: false
+keep_c0_init: true
+kl_min: 0
+kl_start_steps: 1
+lat_for_dur: false
+latent_dim: 16
+latent_size: 256
+layers_in_block: 2
+ling_label_dict_size:
+- 20
+- 4
+- 5
+- 2
+- 3
+- 3
+- 3
+- 6
+- 15
+ling_labels:
+- tone
+load_ckpt: ''
+loud_norm: false
+mel_vmax: 0.5
+mel_vmin: -6
+min_frames: 50
+mixed_precision: bf16
+no_text_enc: false
+nsf_type: none
+num_heads: 2
+out_wav_norm: true
+pad_frames: false
+
+precision: fp16
+predict_pitch: false
+resblock: '1'
+resblock_dilation_sizes:
+- - 1
+  - 3
+  - 5
+- - 1
+  - 3
+  - 5
+- - 1
+  - 3
+  - 5
+resblock_kernel_sizes:
+- 3
+- 7
+- 11
+train_spk_embed_only: false
+upsample_initial_channel: 512
+upsample_kernel_sizes:
+- 12
+- 11
+- 8
+- 4
+upsample_rates:
+- 6
+- 5
+- 4
+- 2
+use_bert_input: false
+use_cfg: true
+use_char: true
+use_cur_global: false
+use_cur_global_dec: true
+use_dur_embed: true
+use_dur_mask_embed: true
+use_ema: false
+use_expand_ph: true
+use_finegrained_spk: false
+use_global_lat: false
+use_gt_dur: false
+use_gt_f0: false
+use_mix_spk_embed: false
+use_new_vae: false
+use_ph_level_f0: false
+use_ph_pos_embed: true
+use_pitch_embed: false
+use_pitch_embed_dec: false
+use_pitch_pred: true
+use_pos_embed: true
+use_qk_norm: true
+use_random_spk_embed: false
+use_seq_cfg: true
+use_spk_embed: false
+use_spk_enc: true
+use_spk_id: false
+use_uv: true
+use_vae: true
+use_vpcfm: true
+use_vqvae: true
+use_word_encoder: true
+use_word_input: false
+vae_dur_grad: 0.1
+vae_enc_hidden_size: 384
+vae_stride: 4
+vae_word_conder_layers: 0
+vq_stride: 8
+win_size: 1200
+word_dict_size: 10000
+melgan_config:
+  all_noise: false
+  backbone_resampling: librosa_kaiser_best
+  batch_size: 8
+  cond_disc: false
+  dim_pitch_condition: 1
+  downsamp_factor: 4
+  epochs: 1000
+  frame_shift: 240
+  lambda_feat: 0.0
+  lambda_log_pitch: 0.4
+  lambda_voiced: 1.0
+  load_D: 1
+  log_interval: 100
+  loss_pitch: 1.0
+  loss_speaker: 1.0
+  loss_stft: 0.0
+  lr: 0.0005
+  mode_pitch_condition: singgan_torch
+  multi_resolution: 0
+  n_layers_D: 4
+  n_mel_channels: 160
+  n_residual_layers: 4
+  n_test_samples: 5
+  ndf: 16
+  noise_index: 1.0
+  nr: 0
+  num_D: 3
+  num_band: 1
+  num_workers: 0
+  offset: 0
+  pretrain_steps: 0
+  res_layers: 1
+  run_hdfs: 0
+  sampling_rate: 24000
+  save_interval: 5000
+  seq_len: 100
+  single_stft: 0
+  sub_dis: 1
+  tf: 1
+  tf_end_ratio: 0.0
+  tf_end_step: 0
+  tf_start_ratio: 0.0
+  tf_start_step: 0
+  up_sample:
+  - 5
+  - 4
+  - 4
+  - 3
+  use_F_dis: 0
+  use_aug_pitch: 0
+  use_interpolate: 0
+  use_lsgan: 1
+  use_mel_loss: 1
+  use_melnorm: 0
+  use_msg_gan: 0
+  use_pitch_condition: false
+  use_pitch_prediction: 1
+  use_sbd: 0
+  use_speaker_prediction: 0
+  use_tanh: true
+  use_time_loss: 1

wavvae/model_only_last.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f432d0740f5238c573be49097a69ac5271e24d0d310e6ea63023f038e5e408a
+size 1022420843