whisper-large-v3-turbo-german-ct2

whisper-large-v3-turbo-german-ct2

CTranslate2 conversion of primeline/whisper-large-v3-turbo-german for use with faster-whisper.

Weights are kept in bfloat16 (the base model is bf16-trained — converting to float16 silently truncates multi-segment transcription, see faster-whisper#567). On Ampere+ GPUs load with compute_type="bfloat16"; on GPUs without bf16 support (e.g. T4) load with compute_type="float32" — widening bf16 → float32 is lossless.

Conversion

ct2-transformers-converter \
  --model primeline/whisper-large-v3-turbo-german \
  --output_dir whisper-large-v3-turbo-german-ct2 \
  --quantization bfloat16 \
  --copy_files preprocessor_config.json
# tokenizer.json generated separately so the model works fully offline (HF_HUB_OFFLINE=1)

Usage

from faster_whisper import WhisperModel

model = WhisperModel("tnfru/whisper-large-v3-turbo-german-ct2",
                     device="cuda", compute_type="bfloat16")
segments, info = model.transcribe("audio.ogg", language="de",
                                  beam_size=15, best_of=5)
print(" ".join(s.text for s in segments))

License

Inherits the license of the base model.