Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
ctl
/
wav2vec2-large-xlsr-cantonese
like
13
Automatic Speech Recognition
Transformers
PyTorch
JAX
common_voice
Yue Chinese
wav2vec2
audio
speech
xlsr-fine-tuning-week
Eval Results (legacy)
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
3
Deploy
Use this model
refs/pr/3
wav2vec2-large-xlsr-cantonese
5.07 GB
4 contributors
History:
28 commits
librarian-bot
Librarian Bot: Add base_model information to model
9d5f837
about 2 years ago
.gitattributes
736 Bytes
allow flax
over 4 years ago
README.md
4.09 kB
Librarian Bot: Add base_model information to model
about 2 years ago
cer.py
3.83 kB
fix doc
almost 5 years ago
cer_memory_efficient.py
9.99 kB
cer impl for colab
almost 5 years ago
config.json
1.57 kB
Update model
almost 5 years ago
flax_model.msgpack
1.28 GB
xet
upload flax model
over 4 years ago
optimizer.pt
2.52 GB
xet
Update model
almost 5 years ago
preprocessor_config.json
158 Bytes
Add model files
almost 5 years ago
pytorch_model.bin
1.28 GB
xet
Update model
almost 5 years ago
scheduler.pt
623 Bytes
xet
Update model
almost 5 years ago
special_tokens_map.json
85 Bytes
Add model files
almost 5 years ago
test_cer.py
4.76 kB
upadte CER
almost 5 years ago
tokenizer_config.json
138 Bytes
Add model files
almost 5 years ago
trainer_state.json
23.5 kB
Update model
almost 5 years ago
training_args.bin
2.29 kB
xet
Update model
almost 5 years ago
vocab.json
45.4 kB
Update model
almost 5 years ago