comodoro
/

wav2vec2-xls-r-300m-cs-250

Automatic Speech Recognition

Generated from Trainer

hf-asr-leaderboard

mozilla-foundation/common_voice_8_0

robust-speech-event

xlsr-fine-tuning-week

Inference Endpoints

Model card Files Files and versions Community

wav2vec2-xls-r-300m-cs-250

4 contributors

History: 16 commits

comodoro's picture

LM attempt

627cbf9 almost 3 years ago

language_model
LM attempt almost 3 years ago
.gitattributes

1.18 kB

initial commit almost 3 years ago
Fine_Tune_XLS_R_on_Common_Voice_cs_300m_CV8.ipynb

362 kB

Add the notebook used almost 3 years ago
README.md

6.04 kB

Update README.md almost 3 years ago
added_tokens.json

23 Bytes

Add missing metadata almost 3 years ago
alphabet.json

343 Bytes

LM attempt almost 3 years ago
config.json

2.07 kB

Added further fine-tuned model almost 3 years ago
eval.py

5.03 kB

Fix eval script almost 3 years ago
preprocessor_config.json

262 Bytes

LM attempt almost 3 years ago
pytorch_model.bin

1.26 GB
LFS

Added further fine-tuned model almost 3 years ago
rng_state.pth
Detected Pickle imports (7)
- "torch.ByteStorage",
- "_codecs.encode",
- "torch._utils._rebuild_tensor_v2",
- "numpy.ndarray",
- "numpy.core.multiarray._reconstruct",
- "collections.OrderedDict",
- "numpy.dtype"
How to fix it?
14.6 kB
LFS

Initial CV 8.0 model almost 3 years ago
special_tokens_map.json

309 Bytes

Add missing metadata almost 3 years ago
tokenizer_config.json

300 Bytes

Add missing metadata almost 3 years ago
trainer_state.json

2.76 kB

Added further fine-tuned model almost 3 years ago
vocab.json

409 Bytes

Add missing metadata almost 3 years ago