Downloads · 30 days
9
16% of all-time downloads
faster-whisper-large-v3-8bit
castle1996/faster-whisper-large-v3-8bit
faster-whisper-large-v3-8bit is a automatic speech recognition model from castle1996. Use it when you need speech turned into text. It is set up for ctranslate2. The card lists the license as mit.
This model is converted from openai/whisper-large-v3 to the CTranslate2 format using INT8 quantization, primarily for use with faster-whisper
All-time downloads
55
Public
Repo size
1.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.6 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- ctranslate2
- License
- mit
- Access
- Public
- Created
- May 16, 2026
- Updated
- May 16, 2026
- SHA
- e8c824e8
Base models
Model card
From the Hugging Face model README
CTranslate2 Conversion of whisper-large-v3 (INT8 Quantization)
This model is converted from openai/whisper-large-v3 to the CTranslate2 format using INT8 quantization, primarily for use with faster-whisper
Model Details
For more details about the model, see its original model card
Conversion Details
The original model was converted using the following command:
ct2-transformers-converter --model whisper-large-v3-turbo --copy_files tokenizer.json preprocessor_config.json --output_dir faster-whisper-large-v3-turbo-int8-ct2 --quantization int8
- Task
- Automatic Speech Recognition
- Library
- ctranslate2
- License
- mit
- Languages
- en, zh, de, es, ru, ko
- Created
- May 16, 2026
- Updated
- May 16, 2026