metadata
license: apache-2.0
language:
- ca
datasets:
- projecte-aina/3catparla_asr
tags:
- audio
- automatic-speech-recognition
- catalan
- faster-whisper
- whisper-large-v3
- catalonia
- barcelona-supercomputing-center
- projecte-aina
- 3catparla
faster-whisper-large-v3-ca-3catparla
This is a faster-whisper version of projecte-aina/whisper-large-v3-ca-3catparla.
The specific dataset used to create the model is the 3CatParla.
The model was created like described in faster-whisper:
ct2-transformers-converter --model projecte-aina/whisper-large-v3-ca-3catparla
--output_dir faster-whisper-large-v3-ca-3catparla
--copy_files preprocessor_config.json
--quantization float16
Usage
from faster_whisper import WhisperModel
model_size = "projecte-aina/faster-whisper-large-v3-ca-3catparla"
# Run on GPU with FP16
model = WhisperModel(model_size, device="cuda", compute_type="float16")
# or run on GPU with INT8
#model = WhisperModel(model_size, device="cuda", compute_type="int8_float16")
# or run on CPU with INT8
# model = WhisperModel(model_size, device="cpu", compute_type="int8")
segments, info = model.transcribe("audio_in_catalan.mp3", beam_size=5, task="translate",language="ca")
print("Detected language '%s' with probability %f" % (info.language, info.language_probability))
for segment in segments:
print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
BibTeX entry and citation info
- When publishing results based on these models please refer to:
@misc{mena2024fastwhis3catparla,
title={Acoustic Model in Catalan: faster-whisper-large-v3-ca-3catparla.},
author={Hernandez Mena, Carlos Daniel},
organization={Barcelona Supercomputing Center},
url={https://huggingface.co/projecte-aina/faster-whisper-large-v3-ca-3catparla},
year={2024},
}
Acknowledgements
This model has been promoted and financed by the Government of Catalonia through the Aina project.