Indicwav2vec Hindi

🚀 IndicWav2Vec-Hindi

This is an ASR model in the style of Wav2Vec2, trained using fairseq and ported to Hugging Face. It offers solutions for automatic speech recognition tasks.

🚀 Quick Start

This is a Wav2Vec2 style ASR model trained in fairseq and ported to Hugging Face. More details on datasets, training-setup and conversion to HuggingFace format can be found in the IndicWav2Vec repo.

⚠️ Important Note

This model doesn't support inference with Language Model.

💻 Usage Examples

Basic Usage

import torch
from datasets import load_dataset
from transformers import AutoModelForCTC, AutoProcessor
import torchaudio.functional as F

DEVICE_ID = "cuda" if torch.cuda.is_available() else "cpu"
MODEL_ID = "ai4bharat/indicwav2vec-hindi"

sample = next(iter(load_dataset("common_voice", "hi", split="test", streaming=True)))
resampled_audio = F.resample(torch.tensor(sample["audio"]["array"]), 48000, 16000).numpy()

model = AutoModelForCTC.from_pretrained(MODEL_ID).to(DEVICE_ID)
processor = AutoProcessor.from_pretrained(MODEL_ID)

input_values = processor(resampled_audio, return_tensors="pt").input_values

with torch.no_grad():
    logits = model(input_values.to(DEVICE_ID)).logits.cpu()
    
prediction_ids = torch.argmax(logits, dim=-1)
output_str = processor.batch_decode(prediction_ids)[0]
print(f"Greedy Decoding: {output_str}")

📚 Documentation

About AI4Bharat

• Website: https://ai4bharat.org/
• Code: https://github.com/AI4Bharat
• HuggingFace: https://huggingface.co/ai4bharat

📄 License

This project uses the apache-2.0 license.