Whisper Telugu Base

🚀 Whisper Telugu Base

This model is a fine - tuned version of [openai/whisper - base](https://huggingface.co/openai/whisper - base) on Telugu data from multiple publicly available ASR corpuses. It offers high - quality automatic speech recognition for Telugu.

🚀 Quick Start

This model is a fine - tuned version of openai/whisper-base on the Telugu data sourced from multiple publicly available ASR corpuses. It was fine - tuned as part of the Whisper fine - tuning sprint.

NOTE: The code for training this model can be reused from the whisper-finetune repository.

✨ Features

• Fine - tuned on diverse Telugu ASR corpuses.
• Supports both normal and faster inference methods.

📦 Installation

No specific installation steps are provided in the original README. However, to use the model, you need to have the necessary Python libraries such as torch, transformers, and for faster inference, whisper - jax. You can install them via pip:

pip install torch transformers
pip install git+https://github.com/sanchit-gandhi/whisper-jax

💻 Usage Examples

Basic Usage

In order to infer a single audio file using this model, the following code snippet can be used:

>>> import torch
>>> from transformers import pipeline

>>> # path to the audio file to be transcribed
>>> audio = "/path/to/audio.format"
>>> device = "cuda:0" if torch.cuda.is_available() else "cpu"

>>> transcribe = pipeline(task="automatic-speech-recognition", model="vasista22/whisper-telugu-base", chunk_length_s=30, device=device)
>>> transcribe.model.config.forced_decoder_ids = transcribe.tokenizer.get_decoder_prompt_ids(language="te", task="transcribe")

>>> print('Transcription: ', transcribe(audio)["text"])

Advanced Usage

For faster inference of whisper models, the whisper-jax library can be used. Please follow the necessary installation steps as mentioned here, before using the following code snippet:

>>> import jax.numpy as jnp
>>> from whisper_jax import FlaxWhisperForConditionalGeneration, FlaxWhisperPipline

>>> # path to the audio file to be transcribed
>>> audio = "/path/to/audio.format"

>>> transcribe = FlaxWhisperPipline("vasista22/whisper-telugu-base", batch_size=16)
>>> transcribe.model.config.forced_decoder_ids = transcribe.tokenizer.get_decoder_prompt_ids(language="te", task="transcribe")

>>> print('Transcription: ', transcribe(audio)["text"])

📚 Documentation

Evaluation

To evaluate this model on an entire dataset, use the evaluation codes in the whisper-finetune repository.

Faster Inference

The same repository also provides scripts for faster inference using whisper - jax.

🔧 Technical Details

Training and Evaluation Data

Training Hyperparameters

📄 License

This project is licensed under the Apache - 2.0 license.

Acknowledgement

This work was carried out at Speech Lab, IIT Madras. The compute resources were funded by the "Bhashini: National Language translation Mission" project of the Ministry of Electronics and Information Technology (MeitY), Government of India.

Model Index