whisper large-v2 fine-tuned on CommonVoice Serbian

This repository provides all the necessary tools to perform automatic speech recognition from an end-to-end whisper model fine-tuned on CommonVoice (Serbian Language) within SpeechBrain. For a better experience, we encourage you to learn more about SpeechBrain.

The performance of the model is the following:

Release	Test CER	Test WER	GPUs
01-02-23	7.60	23.63	1xV100 16GB

Pipeline description

This ASR system is composed of whisper encoder-decoder blocks:

The pretrained whisper-large-v2 encoder is frozen.
The pretrained Whisper tokenizer is used.
A pretrained Whisper-large-v2 decoder (openai/whisper-large-v2) is finetuned on CommonVoice Sr. The obtained final acoustic representation is given to the greedy decoder.

The system is trained with recordings sampled at 16kHz (single channel). The code will automatically normalize your audio (i.e., resampling + mono channel selection) when calling transcribe_file if needed.

Install SpeechBrain

First of all, please install tranformers and SpeechBrain with the following command:

pip install speechbrain transformers==4.28.0

Please notice that we encourage you to read our tutorials and learn more about SpeechBrain.

Transcribing your own audio files (in Serbian)


from speechbrain.inference.ASR import WhisperASR

asr_model = WhisperASR.from_hparams(source="speechbrain/asr-whisper-large-v2-commonvoice-sr", savedir="pretrained_models/asr-whisper-large-v2-commonvoice-sr")
asr_model.transcribe_file("speechbrain/asr-whisper-large-v2-commonvoice-sr/example-sr.wav")

Inference on GPU

To perform inference on the GPU, add run_opts={"device":"cuda"} when calling the from_hparams method.

Training

The model was trained with SpeechBrain. To train it from scratch follow these steps:

Clone SpeechBrain:

git clone https://github.com/speechbrain/speechbrain/

Install it:

cd speechbrain
pip install -r requirements.txt
pip install -e .

Run Training:

cd recipes/CommonVoice/ASR/transformer/
python train_with_whisper.py hparams/train_sr_hf_whisper.yaml --data_folder=your_data_folder

You can find our training results (models, logs, etc) here.

Limitations

The SpeechBrain team does not provide any warranty on the performance achieved by this model when used on other datasets.

Referencing SpeechBrain

@misc{SB2021,
    author = {Ravanelli, Mirco and Parcollet, Titouan and Rouhe, Aku and Plantinga, Peter and Rastorgueva, Elena and Lugosch, Loren and Dawalatabad, Nauman and Ju-Chieh, Chou and Heba, Abdel and Grondin, Francois and Aris, William and Liao, Chien-Feng and Cornell, Samuele and Yeh, Sung-Lin and Na, Hwidong and Gao, Yan and Fu, Szu-Wei and Subakan, Cem and De Mori, Renato and Bengio, Yoshua },
    title = {SpeechBrain},
    year = {2021},
    publisher = {GitHub},
    journal = {GitHub repository},
    howpublished = {\\\\url{https://github.com/speechbrain/speechbrain}},
  }

About SpeechBrain

SpeechBrain is an open-source and all-in-one speech toolkit. It is designed to be simple, extremely flexible, and user-friendly. Competitive or state-of-the-art performance is obtained in various domains.

Website: https://speechbrain.github.io/

GitHub: https://github.com/speechbrain/speechbrain

speechbrain
/

asr-whisper-large-v2-commonvoice-sr