You can deploy this model and start earning money today!

Jeremy-p/
whisper-small-qc-fr-ct2-int8

Name: whisper-small-qc-fr-ct2-int8
Availability: InStock

automatic-speech-recognition

Jeremy-p/whisper-small-qc-fr

quantized

mit

Views

No views yet

whisper-small-qc-fr — CTranslate2 int8

CTranslate2 int8 quantization of Jeremy-p/whisper-small-qc-fr, openai/whisper-small fully fine-tuned on a Quebec-French-weighted French/English mix (fr sampling probability 0.90 / en 0.10). 242 MB, for use with faster-whisper.

Training

Full fp32 fine-tune (fp16-autocast mixed precision), gradient checkpointing, 2-GPU DDP. French and English training data mixed via datasets.interleave_datasets(probabilities=[0.90, 0.10], stopping_strategy="first_exhausted"). Labels truncated/filtered at a 448-token max length. Quantized to int8 via ct2-transformers-converter after fine-tuning.

Results

French, n=100:

Model	WER
`openai/whisper-small` (stock)	49.0%
`faster-whisper` `base` int8	66.9%
`Qwen3-ASR-0.6B`	40.3%
this model, fp32	37.9%
this model, ct2 int8	35.1%

English, n=324:

Model	WER
`openai/whisper-small` (stock)	5.67%
`faster-whisper` `base` int8	6.13%
`Qwen3-ASR-0.6B`	2.34%
this model, fp32	3.51%
this model, ct2 int8	3.69%

int8 quantization costs roughly 0.2pt WER on English relative to fp32 (3.51% → 3.69%, ~5% relative).

Usage

python

from faster_whisper import WhisperModel

model = WhisperModel("Jeremy-p/whisper-small-qc-fr-ct2-int8", compute_type="int8")
segments, info = model.transcribe("audio.wav", language="fr")
print("".join(seg.text for seg in segments))

The fp32 Transformers checkpoint is at Jeremy-p/whisper-small-qc-fr.

License

MIT