Initial commit

README.md

@@ -0,0 +1,144 @@
+---
+language:
+- en
+- hi
+- or
+- bn
+- ta
+- te
+- kn
+- ml
+- mr
+- gu
+- pa
+- as
+license: apache-2.0
+pipeline_tag: audio-classification
+library_name: transformers
+tags:
+- language-identification
+- indian-languages
+- multilingual
+- speech
+- asr-preprocessing
+- callcenter-ai
+- speech-analytics
+- audio-classification
+- wav2vec2
+- transformers
+- pytorch
+- huggingface
+---
+
+# **Vakgyata**
+
+**Language Identification for Indian Languages from Speech**
+
+---
+
+## **Model Overview**
+
+`vakgyata` is an open-source language identification model specifically designed to classify Indian languages from raw speech audio. It is built upon the pretrained [`Harveenchadha/wav2vec2-pretrained-clsril-23-10k`](https://huggingface.co/Harveenchadha/wav2vec2-pretrained-clsril-23-10k) with additional **Layer Normalization** integrated to improve stability and performance for audio classification tasks.
+
+---
+
+## **Variants and Model Sizes**
+
+| Variant          | Parameters | Accuracy |
+| ---------------- | ---------- | -------- |
+| `vakgyata-base`  | 95M        | 95.88%   |
+| `vakgyata-small` | 52M        | 95.06%   |
+| `vakgyata-mini`  | 38M        | 95.06%   |
+| `vakgyata-tiny`  | 24M        | 93.63%   |
+
+---
+
+## **Supported Languages**
+
+| Language        | Code  |
+| --------------- | ----- |
+| English (India) | en-IN |
+| Hindi           | hi-IN |
+| Odia            | or-IN |
+| Bengali         | bn-IN |
+| Tamil           | ta-IN |
+| Telugu          | te-IN |
+| Kannada         | kn-IN |
+| Malayalam       | ml-IN |
+| Marathi         | mr-IN |
+| Gujarati        | gu-IN |
+| Punjabi         | pa-IN |
+| Assamese        | as-IN |
+
+---
+
+## **Specifications**
+
+* **Supported Sampling Rate:** 16000 Hz
+* **Recommended Audio Format:** 16kHz, 16bit PCM (Mono)
+
+---
+
+## **Installation**
+
+```bash
+pip install transformers torchaudio
+```
+
+---
+
+## **Usage**
+
+```python
+from transformers import Wav2Vec2ForSequenceClassification, AutoFeatureExtractor
+import torch
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+model_id = "onecxi/vakgyata-mini"
+
+processor = AutoFeatureExtractor.from_pretrained(model_id)
+model = Wav2Vec2ForSequenceClassification.from_pretrained(model_id).to(device)
+```
+
+---
+
+## **Inference Example**
+
+```python
+import torchaudio
+
+# Load the audio (ensure it's 16kHz mono)
+audio, sr = torchaudio.load("path/to/audio.wav")
+
+# Preprocess
+inputs = processor(audio.squeeze(), sampling_rate=sr, return_tensors="pt").to(device)
+
+# Inference
+with torch.no_grad():
+    logits = model(**inputs).logits
+
+# Softmax to get probabilities
+probs = logits.softmax(dim=-1).cpu().numpy()
+
+# Predicted language
+language = model.config.id2label.get(probs.argmax())
+print("Predicted Language:", language)
+```
+
+---
+
+## **Citation**
+
+If you use this model in your research or application, please consider citing the model and its base source:
+
+```
+@misc{vakgyata2024,
+  title={vakgyata: Language Identification for Indian Speech},
+  author={OneCXI},
+  year={2024},
+  url={https://huggingface.co/onecxi/vakgyata-base}
+}
+```
+
+---

config.json

@@ -0,0 +1,143 @@
+{
+  "_name_or_path": "onecxi/vakgyata-mini",
+  "activation_dropout": 0.1,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token": "<s>",
+  "bos_token_id": 1,
+  "classifier_proj_size": 1024,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_lower_case": false,
+  "do_stable_layer_norm": true,
+  "eos_token": "</s>",
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "en-IN",
+    "1": "hi-IN",
+    "2": "or-IN",
+    "3": "bn-IN",
+    "4": "ta-IN",
+    "5": "te-IN",
+    "6": "kn-IN",
+    "7": "ml-IN",
+    "8": "mr-IN",
+    "9": "gu-IN",
+    "10": "pa-IN",
+    "11": "as-IN"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "as-IN": 11,
+    "bn-IN": 3,
+    "en-IN": 0,
+    "gu-IN": 9,
+    "hi-IN": 1,
+    "kn-IN": 6,
+    "ml-IN": 7,
+    "mr-IN": 8,
+    "or-IN": 2,
+    "pa-IN": 10,
+    "ta-IN": 4,
+    "te-IN": 5
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "model_name": "vakgyata",
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 12,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 4,
+  "num_negatives": 100,
+  "output_hidden_size": 768,
+  "pad_token": "[PAD]",
+  "pad_token_id": 0,
+  "proj_codevector_dim": 256,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "unk_token": "[UNK]",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 12,
+  "word_delimiter_token": "|",
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64737b2f254b46e13b471c9090299e886a6b5ccb98b02a989e5ef840dc1924e9
+size 153884320

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18d0db5d829d46e8e26bf028d101a33d388aac1c92dedb571a800b4b7ff35a48
+size 154004514

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}