Kodavoice Singlish

--- license: mit language: - en library_name: ctranslate2 pipeline_tag: automatic-speech-recognition base_model: - mjwong/whisper-large-v3-turbo-singlish tags: - automatic-speech-recognition - whisper - ctranslate2 - faster-whisper - singlish - singapore - southeast-asia --- # KodaVoice Singlish — CTranslate2 (int8) A [CTranslate2](https://github.com/OpenNMT/CTranslate2) **int8** conversion of [`mjwong/whisper-large-v3-turbo-singlish`](https://huggingface.co/mjwong/whisper-large-v3-turbo-singlish), packaged so it loads directly in [faster-whisper](https://github.com/SYSTRAN/faster-whisper). Used as the default dictation model in **KodaVoice** for Singlish / Singapore–Malaysia English. Only the *format* changed (PyTorch → CTranslate2, int8 quantization) — the weights are the source fine-tune's, unmodified. ## Usage ```python from faster_whisper import WhisperModel model = WhisperModel("salvestr0/kodavoice-singlish", device="cpu", compute_type="int8") segments, info = model.transcribe("audio.wav", beam_size=1) for s in segments: print(s.text) ``` `beam_size=1` (greedy) is the recommended mode — beam search does not improve WER on this fine-tune. ### whisper.cpp (GGML) For the whisper.cpp / Vulkan runtime, this repo also ships a q5_0 GGML build (`ggml-kodavoice-singlish-q5_0.bin`, ~547 MB — same size/quality tier as the stock `ggml-large-v3-turbo-q5_0`): ```bash whisper-cli -m ggml-kodavoice-singlish-q5_0.bin -f audio.wav -l en ``` ## Scope & honest limits The fine-tune's accuracy gains are validated on **Singapore + Malaysia English / Singlish**. It is not a validated fine-tune for Philippine, Indonesian, Thai, or Vietnamese English — treat those as vanilla Whisper large-v3-turbo behaviour. ## Attribution & license - **Source fine-tune:** [`mjwong/whisper-large-v3-turbo-singlish`](https://huggingface.co/mjwong/whisper-large-v3-turbo-singlish) — MIT, © mjwong - **Base model:** [`openai/whisper-large-v3-turbo`](https://huggingface.co/openai/whisper-large-v3-turbo) — MIT - This derivative is released under **MIT**. See [`NOTICE`](./NOTICE) for full attribution.

Source context: 15 downloads · 0 likes · Pipeline automatic-speech-recognition · Library ctranslate2 · Repo salvestr0/kodavoice-singlish

Source context: 12 downloads · 0 likes · Pipeline automatic-speech-recognition · Library ctranslate2 · Repo salvestr0/kodavoice-singlish