Downloads · 30 days
57
24% of all-time downloads
digikar/vasista22-whisper-hindi-large-v2-ct2-int8
vasista22-whisper-hindi-large-v2-ct2-int8 is a automatic speech recognition model from digikar. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
int8 quantized ctranslate2-compatible version of vasista22/whisper-hindi-large-v2. This means the 5.7GB model is compressed into 1.6GB :).
Downloads · 30 days
57
24% of all-time downloads
All-time downloads
237
Public
Repo size
1.6 GB
Likes
0
Public
Click a slice to open those files.
.bin1.6 GB · 100%
From the Hugging Face model README
int8 quantized ctranslate2-compatible version of vasista22/whisper-hindi-large-v2. This means the 5.7GB model is compressed into 1.6GB :).
Model created using
ct2-transformers-converter --model /path/to/vasista22/whisper-hindi-large-v2 --output_dir whisper-hindi-large-v2-ct2-int8 --copy_files tokenizer_config.json preprocessor_config.json added_tokens.json special_tokens_map.json --quantization int8
For monospeaker audio, use either of
For multispeaker audio with english diarization, use whisperX.
For multispeaker audio with non-english diarization, use whisper-diarization.