carlosdanielhernandezmena's picture
Fixing bibtex format
2918ffe
metadata
license: cc-by-4.0
language: mt
datasets:
  - common_voice
tags:
  - audio
  - automatic-speech-recognition
  - maltese
  - whisper-large
  - whisper-large-v1
  - masri-project
  - malta
  - university-of-malta
  - faster-whisper

whisper-large-maltese-8k-steps-64h-ct2

This is a faster-whisper version of carlosdanielhernandezmena/whisper-large-maltese-8k-steps-64h-ct2.

Most of the data used to create this model is available at the the MASRI Project homepage.

The model was created like described in faster-whisper:

ct2-transformers-converter --model carlosdanielhernandezmena/whisper-large-maltese-8k-steps-64h \
    --output_dir whisper-large-maltese-8k-steps-64h-ct2 \
    --quantization float16

Usage

from faster_whisper import WhisperModel

model_size = "whisper-large-maltese-8k-steps-64h-ct2"

# 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.mp3", beam_size=5)

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{mena2023whisperlargemaltesect2,
      title={Acoustic Model in Maltese: whisper-large-maltese-8k-steps-64h-ct2.}, 
      author={Hernandez Mena, Carlos Daniel},
      url={https://huggingface.co/carlosdanielhernandezmena/whisper-large-maltese-8k-steps-64h-ct2},
      year={2023}
}

Acknowledgements

The MASRI Project is funded by the University of Malta Research Fund Awards. We want to thank to Merlin Publishers (Malta) for provinding the audiobooks used to create the MASRI-MERLIN Corpus.

Thanks to Jón Guðnason, head of the Language and Voice Lab for providing computational power to make this model possible. We also want to thank to the "Language Technology Programme for Icelandic 2019-2023" which is managed and coordinated by Almannarómur, and it is funded by the Icelandic Ministry of Education, Science and Culture.

Special thanks to Björn Ingi Stefánsson for setting up the configuration of the server where this model was trained.