Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Jacaranda-Health
/
ASR-STT-4bit
like
1
Follow
Jacaranda Health
10
Automatic Speech Recognition
Safetensors
English
Swahili
whisper
speech-to-text
quantized
4bit
4-bit precision
bitsandbytes
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
main
ASR-STT-4bit
485 MB
2 contributors
History:
6 commits
eolang
Update README.md
163d93a
verified
4 months ago
.gitattributes
1.52 kB
initial commit
5 months ago
README.md
2 kB
Update README.md
4 months ago
added_tokens.json
34.6 kB
Add processor for 4-bit quantized model
5 months ago
config.json
1.81 kB
Add 4-bit quantized speech-to-text model
5 months ago
generation_config.json
3.68 kB
Add 4-bit quantized speech-to-text model
5 months ago
merges.txt
494 kB
Add processor for 4-bit quantized model
5 months ago
model.safetensors
483 MB
xet
Add 4-bit quantized speech-to-text model
5 months ago
normalizer.json
52.7 kB
Add processor for 4-bit quantized model
5 months ago
preprocessor_config.json
356 Bytes
Add processor for 4-bit quantized model
5 months ago
special_tokens_map.json
2.19 kB
Add processor for 4-bit quantized model
5 months ago
tokenizer_config.json
283 kB
Add processor for 4-bit quantized model
5 months ago
vocab.json
1.04 MB
Add processor for 4-bit quantized model
5 months ago