Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
rosyvs
/
whisat-base
like
0
Automatic Speech Recognition
Transformers
whisper
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
whisat-base
1.46 GB
Ctrl+K
Ctrl+K
2 contributors
History:
8 commits
rosyvs
Create README.md
f4ea25e
almost 3 years ago
.gitattributes
Safe
1.48 kB
initial commit
almost 3 years ago
CKPT.yaml
Safe
141 Bytes
first commit - version 202_base-en_v1 model run. trained without augmentation
almost 3 years ago
README.md
Safe
59 Bytes
Create README.md
almost 3 years ago
brain.ckpt
50 Bytes
xet
first commit - version 202_base-en_v1 model run. trained without augmentation
almost 3 years ago
config.json
Safe
1.94 kB
first commit - version 202_base-en_v1 model run. trained without augmentation
almost 3 years ago
counter.ckpt
Safe
1 Bytes
xet
first commit - version 202_base-en_v1 model run. trained without augmentation
almost 3 years ago
dataloader-TRAIN.ckpt
5 Bytes
xet
first commit - version 202_base-en_v1 model run. trained without augmentation
almost 3 years ago
decoder.ckpt
291 MB
xet
first commit - version 202_base-en_v1 model run. trained without augmentation
almost 3 years ago
infer_hf_whisper.yaml
Safe
2.58 kB
add save_path direclty to yaml same as sb example
almost 3 years ago
optimizer.ckpt
581 MB
xet
first commit - version 202_base-en_v1 model run. trained without augmentation
almost 3 years ago
preprocessor_config.json
Safe
185 kB
first commit - version 202_base-en_v1 model run. trained without augmentation
almost 3 years ago
scaler.ckpt
557 Bytes
xet
first commit - version 202_base-en_v1 model run. trained without augmentation
almost 3 years ago
scheduler_whisper.ckpt
515 Bytes
xet
first commit - version 202_base-en_v1 model run. trained without augmentation
almost 3 years ago
tokenizer.ckpt
291 MB
xet
first commit - version 202_base-en_v1 model run. trained without augmentation
almost 3 years ago
tokenizer.json
2.13 MB
first commit - version 202_base-en_v1 model run. trained without augmentation
almost 3 years ago
tokenizer_config.json
Safe
844 Bytes
first commit - version 202_base-en_v1 model run. trained without augmentation
almost 3 years ago
vocab.json
Safe
999 kB
first commit - version 202_base-en_v1 model run. trained without augmentation
almost 3 years ago
whisper.ckpt
291 MB
xet
first commit - version 202_base-en_v1 model run. trained without augmentation
almost 3 years ago