CoolFace
Modelpublic

BSC-LT/whisper-bsc-large-v3-cat

sourceHugging Faceapache-2.0updated 11mo agoView on Hugging Face
2likes121downloads
Model Card

Whisperbsclargev3cat

Table of Contents

<details> <summary>Click to expand</summary>

</details>

Model Description

The "whisper-bsc-large-v3-cat" is an acoustic model suitable for Automatic Speech Recognition in Catalan. It is the result of finetuning the model "openai/whisper-large-v3" with 4700 hours of Catalan data released by the Projecte AINA from Barcelona, Spain.

Intended Uses and Limitations

This model can be used for Automatic Speech Recognition (ASR) in Catalan. The model intends to transcribe Catalan audio files to plain text without punctuation.

<!--

How to Get Started with the Model

To see an updated and functional version of this code, please visit our Notebook -->

Installation

To use this model, you may install datasets and transformers:

Create a virtual environment:

bash
python -m venv /path/to/venv

Activate the environment:

bash
source /path/to/venv/bin/activate

Install the modules:

bash
pip install datasets transformers

For Inference

To transcribe audio in Catalan using this model, you can follow this example:

bash
#Install Prerequisites
pip install torch
pip install datasets
pip install 'transformers[torch]'
pip install evaluate
pip install jiwer
python
#This code works with GPU

#Notice that: load_metric is no longer part of datasets.
#You have to remove it and use evaluate's load instead.
#(Note from November 2024)

import torch
from transformers import WhisperForConditionalGeneration, WhisperProcessor

#Load the processor and model.
MODEL_NAME="BSC-LT/whisper-bsc-large-v3-cat"
processor = WhisperProcessor.from_pretrained(MODEL_NAME)
model = WhisperForConditionalGeneration.from_pretrained(MODEL_NAME).to("cuda")

#Load the dataset
from datasets import load_dataset, load_metric, Audio
ds=load_dataset("projecte-aina/parlament_parla",split='test')

#Downsample to 16 kHz
ds = ds.cast_column("audio", Audio(sampling_rate=16_000))

#Process the dataset
def map_to_pred(batch):
	audio = batch["audio"]
	input_features = processor(audio["array"], sampling_rate=audio["sampling_rate"], return_tensors="pt").input_features
	batch["reference"] = processor.tokenizer._normalize(batch['normalized_text'])

	with torch.no_grad():
		predicted_ids = model.generate(input_features.to("cuda"))[0]
	
	transcription = processor.decode(predicted_ids)
	batch["prediction"] = processor.tokenizer._normalize(transcription)
	
	return batch
	
#Do the evaluation
result = ds.map(map_to_pred)

#Compute the overall WER now.
from evaluate import load

wer = load("wer")
WER=100 * wer.compute(references=result["reference"], predictions=result["prediction"])
print(WER)

Training Details

Training data

The specific datasets used to create the model are:

Training procedure

This model is the result of fine-tuning the model "openai/whisper-large-v3" by following this tutorial provided by Language Technologies Laboratory. (Soon to be published)

Training Hyperparameters

  • —language: Catalan
  • —hours of training audio: 4700
  • —learning rate: 1e-04
  • —sample rate: 16000
  • —train batch size: 16 (x4 GPUs)
  • —eval batch size: 16
  • —numtrainepochs: 10
  • —weight_decay: 1e-4

Citation

If this model contributes to your research, please cite the work: <!--

bibtex
@inproceedings{hernandez20243catparla,
  title={3CatParla: A New Open-Source Corpus of Broadcast TV in Catalan for Automatic Speech Recognition},
  author={Hern{\'a}ndez Mena, Carlos Daniel and Armentano Oller, Carme and Solito, Sarah and K{\"u}lebi, Baybars},
  booktitle={Proc. IberSPEECH 2024},
  pages={176--180},
  year={2024}
}

-->

bibtext
@misc{takanori2025whisperbsclarge3cat,
      title={Acoustic Model in Catalan: Whisper_bsc_large_v3_cat.}, 
      author={Sanchez Shiromizu, Lucas Takanori; Hernandez Mena, Carlos Daniel; Messaoudi, Abir; España i Bonet, Cristina; Cortada Garcia, Marti},
      organization={Barcelona Supercomputing Center},
      url={https://huggingface.co/langtech-veu/whisper-bsc-large-v3-cat},
      year={2025}
}

Additional Information

Author

The fine-tuning process was performed during Spring (2025) in the Language Technologies Laboratory of the Barcelona Supercomputing Center by Lucas Takanori Sanchez Shiromizu.

Contact

For further information, please send an email to <langtech@bsc.es>.

Copyright

Copyright(c) 2025 by Language Technologies Laboratory, Barcelona Supercomputing Center.

License

Apache-2.0

Funding

This work is funded by the Ministerio para la Transformación Digital y de la Función Pública - Funded by EU – NextGenerationEU within the framework of the project ILENIA with reference 2022/TL22/00215337.

The training of the model was possible thanks to the computing time provided by Barcelona Supercomputing Center through MareNostrum 5.