Whisper large-v3-turbo for Scribe SV — CTranslate2, int8
A CTranslate2 build of Whisper large-v3-turbo quantized to int8, for machines without a
CUDA GPU. Used by Scribe SV, a Windows dictation and translation
utility, and published here so the application can download it on demand.
Nothing was retrained or fine-tuned. Converted directly from the official OpenAI weights:
ct2-transformers-converter --model openai/whisper-large-v3-turbo \
--copy_files tokenizer.json preprocessor_config.json \
--output_dir . --quantization int8
The float16 build for GPU machines lives in a separate repository:
crash-sv/scribe-whisper-turbo-fp16.
The two precisions are kept apart on purpose: our downloader fetches a whole repository, so a
CPU-only user should not have to pull the 1.5 GB float16 weights to get these 0.8 GB.
Measured cost of quantization
Measured on our own bench (Russian speech, 194 s of audio with a human reference transcript;
beam_size=5, vad_filter=True, condition_on_previous_text=True, an initial_prompt,
speech_pad_ms=600, hallucination_silence_threshold=2.0):
| float16 on CUDA | int8 on CPU | |
|---|---|---|
| WER | 3.54 % | 4.25 % |
| 194 s file | 3.4 s | 58.2 s |
| short phrase (3-10 s of audio) | 0.18-0.26 s | 5.2-5.8 s |
| punctuation marks per 100 words, spontaneous speech | 31.8 | 26.4 |
Two things worth knowing: the accuracy cost of int8 is small (+0.71 pp WER), but on CPU the
latency of a short phrase is roughly constant at ~5 s regardless of its length — three
seconds of audio and ten seconds of audio both take about that long.
Contents
model.bin, config.json, preprocessor_config.json, tokenizer.json, vocabulary.json —
a complete CTranslate2 model directory.
Usage
from faster_whisper import WhisperModel
from huggingface_hub import snapshot_download
model = WhisperModel(
snapshot_download("crash-sv/scribe-whisper-turbo-int8"),
device="cpu",
compute_type="int8",
)
segments, info = model.transcribe("audio.wav", beam_size=5, vad_filter=True)
Attribution and license
Whisper large-v3-turbo, CTranslate2 int8
- Author: OpenAI (model); Viacheslav Smirnov (int8 conversion)
- License: MIT — https://raw.githubusercontent.com/openai/whisper/main/LICENSE
- Upstream: https://huggingface.co/openai/whisper-large-v3-turbo
- Changes: Our CTranslate2 int8 conversion of the official openai/whisper-large-v3-turbo weights; no retraining.
License text (LICENSE-MIT-openai-whisper.txt) lies in the repository root.
This republication keeps the original licenses.