Downloads · 30 days
25
10% of all-time downloads
ai4bharat/bhili-asr-conformer-600m-onnx
bhili-asr-conformer-600m-onnx is a automatic speech recognition model from ai4bharat. Use it when you need speech turned into text. It is set up for onnx. The card lists the license as mit.
The ONNX version of the Automatic Speech Recognition (ASR) model for Bhili (भीली), specifically the Dehvali Bhili dialect, an Indo-Aryan language spoken by the Bhil community in western India. The NeMo version of the…
Downloads · 30 days
25
10% of all-time downloads
All-time downloads
263
Public
Repo size
7.4 GB
Likes
0
Public
Click a slice to open those files.
Other6.5 GB · 94%
From the Hugging Face model README
The ONNX version of the Automatic Speech Recognition (ASR) model for Bhili (भीली), specifically the Dehvali Bhili dialect, an Indo-Aryan language spoken by the Bhil community in western India. The NeMo version of the model can be found here.
pip install transformers torch torchaudio onnxruntime huggingface_hub
from transformers import AutoModel
import torchaudio
model = AutoModel.from_pretrained(
"ai4bharat/bhili-asr-onnx",
trust_remote_code=True
)
wav, sr = torchaudio.load("audio.wav")
if sr != 16000:
wav = torchaudio.transforms.Resample(sr, 16000)(wav)
if wav.shape[0] > 1:
wav = wav.mean(dim=0, keepdim=True)
text = model(wav, "mr", "ctc")
print(text)
import torch
from transformers import AutoModel
print(f"Using: {'CUDA' if torch.cuda.is_available() else 'CPU'}")
model = AutoModel.from_pretrained(
"ai4bharat/bhili-asr-onnx",
trust_remote_code=True
)
text = model(wav, "mr", "ctc")
Bhili does not currently have a dedicated tokenizer in the IndicConformer model’s supported language set.
We use the Marathi (mr) tokenizer as the closest alternative, since both languages use the Devanagari script.
bhili-asr-onnx/
├── config.json
├── model_onnx.py # HuggingFace inference wrapper
├── README.md
└── assets/
├── preprocessor.ts # Audio preprocessing (TorchScript)
├── encoder.onnx # Conformer encoder (fine-tuned)
├── ctc_decoder.onnx # CTC projection layer
├── rnnt_decoder.onnx # RNN-T prediction network
├── joint_enc.onnx # Joint network encoder projection
├── joint_pred.onnx # Joint network prediction projection
├── joint_pre_net.onnx # Joint pre-network
├── joint_post_net_*.onnx # Language-specific post networks
├── vocab.json # Tokenizer vocabulary
└── language_masks.json # Per-language vocabulary masks