quocphu/PhoWhisper-ct2-FasterWhisper

PhoWhisper-ct2

This repository contains 5 versions of PhoWhisper model converted to use CTranslate2 for faster inference. This allows for significant performance improvements, especially on CPU.

PhoWhisper homepage

PhoWhisper paper

Usage

1. Installation: Ensure you have the necessary libraries installed:

   pip install transformers ctranslate2 faster-whisper
   

2. Download the ct2 model to local (optional): Download the ct2 model you want to use.

3. Transcription:

   import os
   from faster_whisper import WhisperModel
   
   model_size = "quocphu/PhoWhisper-ct2-FasterWhisper/PhoWhisper-medium-ct2-fasterWhisper" # or your model path if you have downloaded
   # 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.wav", beam_size=5) # Replace audio.wav with your audio file
   
   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))
   

Model Details

• Based on the PhoWhisper model.
• Converted using ct2-transformers-converter.
• Optimized for faster inference with CTranslate2.

Contributing

Contributions are welcome! Please open an issue or submit a pull request.

More about Faster-Whisper

Faster-Whisper homepage