Views
No views yet
rhap-llm-audio/Taiwan-Tongues-ASR-CE-pretrainedrhap-llm-audio/faster-Taiwan-Tongues-ASR-CE-pretrainedfloat32 (see CTranslate2 quantization)cpuwhisper-to-faster-whisper1from faster_whisper import WhisperModel
2
3model = WhisperModel(
4 "rhap-llm-audio/faster-Taiwan-Tongues-ASR-CE-pretrained",
5 device="cpu",
6 compute_type="float32",
7)
8segments, info = model.transcribe("audio.mp3")
9for seg in segments:
10 print(f"[{seg.start:.2f} → {seg.end:.2f}] {seg.text}")library_name: ctranslate2, pipeline_tag: automatic-speech-recognition,
language:). After a regular POST /v1/models download, speaches will
list this in GET /v1/models.1curl -X POST http://localhost:8000/v1/models \
2 -H 'Content-Type: application/json' \
3 -d '{"model": "rhap-llm-audio/faster-Taiwan-Tongues-ASR-CE-pretrained"}'
4
5curl http://localhost:8000/v1/audio/transcriptions \
6 -F "file=@audio.mp3" \
7 -F "model=rhap-llm-audio/faster-Taiwan-Tongues-ASR-CE-pretrained"| File | Purpose |
|---|---|
model.bin | CTranslate2 weights (float32) |
config.json | faster-whisper model config |
vocabulary.json | tokenizer vocab |
tokenizer.json | HF tokenizer |
preprocessor_config.json | whisper feature-extractor config |
README.md | this card (speaches filter requires it) |
rhap-llm-audio/Taiwan-Tongues-ASR-CE-pretrained. See source repo for the original model
license. The conversion process itself adds no additional licensing terms.