Downloads · 30 days
85
15% of all-time downloads
nekusu/faster-whisper-large-v3-turbo-latam-int8-ct2
faster-whisper-large-v3-turbo-latam-int8-ct2 is a automatic speech recognition model from nekusu. Use it when you need speech turned into text. The card lists the license as mit.
This model is converted from marianbasti/whisper-large-v3-turbo-latam to the CTranslate2 format using INT8 quantization, primarily for use with faster-whisper.
Downloads · 30 days
85
15% of all-time downloads
All-time downloads
561
Public
Repo size
820 MB
Likes
2
Public
Click a slice to open those files.
.bin820 MB · 100%
From the Hugging Face model README
This model is converted from marianbasti/whisper-large-v3-turbo-latam to the CTranslate2 format using INT8 quantization, primarily for use with faster-whisper.
For more details about the finetuned model, see its original model card.
The original model was converted using the following command:
ct2-transformers-converter --model marianbasti/whisper-large-v3-turbo-latam --copy_files tokenizer.json preprocessor_config.json --output_dir faster-whisper-large-v3-turbo-latam-int8-ct2 --quantization int8
More info on model conversion.
Check Zoont/faster-whisper-large-v3-turbo-int8-ct2 for a quantized version of the original whisper-large-v3-turbo.