PhoWhisper-large-ct2

Fork notice: this is a fork of kiendt/PhoWhisper-large-ct2 (MIT license). Only the model card metadata was changed — library_name: ctranslate2 and tags were added so HF-tag-based discovery/filtering tools (e.g. Speaches) recognize this as a valid CTranslate2 ASR checkpoint. The weights are unmodified, byte-identical to the original repo.

Usage

1. Installation: Ensure you have the necessary libraries installed:
   pip install transformers ctranslate2 faster-whisper
2. Conversion (only needed once): This step converts the original Hugging Face model to the CTranslate2 format.
   ct2-transformers-converter --model vinai/PhoWhisper-large --output_dir PhoWhisper-large-ct2 --copy_files tokenizer_config.json --quantization float16
3. Transcription:
   python

   1import os 2from faster_whisper import WhisperModel 3 4model_size = "kiendt/PhoWhisper-large-ct2" 5# Run on GPU with FP16 6#model = WhisperModel(model_size, device="cuda", compute_type="float16") 7 8# or run on GPU with INT8 9# model = WhisperModel(model_size, device="cuda", compute_type="int8_float16") 10# or run on CPU with INT8 11model = WhisperModel(model_size, device="cpu", compute_type="int8") 12 13segments, info = model.transcribe("audio.wav", beam_size=5) # Replace audio.wav with your audio file 14 15print("Detected language '%s' with probability %f" % (info.language, info.language_probability)) 16 17for segment in segments: 18 print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))

Model Details

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

Contributing

License