| library_name: ctranslate2 | |
| pipeline_tag: automatic-speech-recognition | |
| tags: | |
| - faster-whisper | |
| - whisper-small | |
| - en | |
| license: apache-2.0 | |
| # en__openai__whisper-small__int8 | |
| CTranslate2 export of Whisper Small for `en` (usable with [faster-whisper](https://github.com/SYSTRAN/faster-whisper)). | |
| ## Usage | |
| ```python | |
| from faster_whisper import WhisperModel | |
| model = WhisperModel("en__openai__whisper-small__int8", device="cpu", compute_type="int8") # or cuda / int8_float16 | |
| segments, info = model.transcribe("sample.wav", language="en") | |
| for s in segments: | |
| print(f"[{s.start:.2f} -> {s.end:.2f}] {s.text}") | |
| ``` | |
| > Tip: If you get a language mismatch, pass `language="<code>"` explicitly. | |