Downloads · 30 days
108
34% of all-time downloads
mijuanlo/whisper-large-v3-turbo-ct2-int8
whisper-large-v3-turbo-ct2-int8 is a automatic speech recognition model from mijuanlo. Use it when you need speech turned into text. It is set up for ctranslate2. The card lists the license as mit.
Speedup inference while reducing memory using INT8 quantization with CTranslate2.
Downloads · 30 days
108
34% of all-time downloads
All-time downloads
314
Public
Repo size
814 MB
Likes
1
Public
Click a slice to open those files.
.bin814 MB · 99%
From the Hugging Face model README
Speedup inference while reducing memory using INT8 quantization with CTranslate2.
This is a quantized version of openai/whisper-large-v3-turbo converted to CTranslate2 format.
Compatible with faster-whisper and CTranslate2 directly.
pip install faster-whisper
Checkpoint compatible with CTranslate2 >= 3.22.0
compute_type=int8 for both CPU and GPUfrom faster_whisper import WhisperModel
model = WhisperModel("/path/to/whisper-turbo", device="cuda", compute_type="int8")
segments, info = model.transcribe("audio.mp3", beam_size=5, language="es")
for segment in segments:
print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
This model was converted using ct2-transformers-converter with INT8 quantization. After conversion, the original model files (normalizer.json, preprocessor_config.json, vocab.json, vocabulary.json, etc.) were copied and merged to preserve full compatibility.
ct2-transformers-converter --model openai/whisper-large-v3-turbo --output_dir /path/to/whisper-turbo \
--copy_files tokenizer.json --quantization int8
This model is a quantized version of openai/whisper-large-v3-turbo, which is released under the MIT license. The same license applies to this conversion.
Whisper large-v3-turbo is a optimized variant of Whisper large-v3 from OpenAI. It uses the same 32-layer encoder as large-v3 but with a reduced 4-layer decoder, significantly improving inference speed while maintaining competitive quality.
99 languages: Afrikaans, Arabic, Armenian, Azerbaijani, Belarusian, Bosnian, Bulgarian, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, Galician, German, Greek, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Kannada, Kazakh, Korean, Latvian, Lithuanian, Macedonian, Malay, Marathi, Maori, Nepali, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Serbian, Slovak, Slovenian, Spanish, Swahili, Swedish, Tagalog, Tamil, Thai, Turkish, Ukrainian, Urdu, Vietnamese, Welsh, and more.
Evaluated using Word Error Rate (WER) on LibriSpeech and other benchmarks. See the original model card for detailed metrics.
Whisper was evaluated on LibriSpeech, Common Voice, Fleurs, and other multilingual speech datasets.
Trained on 680,000 hours of multilingual and multitask supervised data collected from the web.
Whisper may transcribe speech inaccurately, particularly for accented speech, low-resource languages, or noisy environments. The model should not be used as a sole decision-making tool in sensitive domains. Whisper's training data was sourced from the web and may contain biases.
Performance varies by language and domain. For best results, use audio with clear speech and minimal background noise. The model is not intended for speaker identification or verification.
Hugging Face: mijuanlo/whisper-large-v3-turbo-ct2-int8