Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
w11wo
/
wav2vec2-xls-r-300m-zh-HK-lm-v2
like
0
Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
common_voice
wav2vec2
Generated from Trainer
hf-asr-leaderboard
robust-speech-event
Eval Results
Inference Endpoints
arxiv:
2111.09296
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
65eae50
wav2vec2-xls-r-300m-zh-HK-lm-v2
/
train_results.json
w11wo
Initial commit
65eae50
almost 3 years ago
raw
Copy download link
history
blame
Safe
197 Bytes
{
"epoch"
:
100.0
,
"train_loss"
:
3.7852419735087786
,
"train_runtime"
:
72640.1075
,
"train_samples"
:
11949
,
"train_samples_per_second"
:
16.45
,
"train_steps_per_second"
:
0.513
}