Hugging Face's logo

Plim
/
xls-r-300m-cv_8-fr

Automatic Speech Recognition
Transformers
PyTorch
French
wav2vec2
mozilla-foundation/common_voice_8_0
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
xls-r-300m-cv_8-fr / wandb /run-20220203_135844-2tzexn1o /files /output.log
Plim's picture
Plim
Training in progress, step 1000
1fb32b9
raw history blame
No virus
4.26 kB
1%|▊ | 100/17440 [12:17<19:56:25, 4.14s/it]
1%|█▋ | 199/17440 [24:34<20:52:21, 4.36s/it]
2%|██▌ | 300/17440 [37:07<20:04:05, 4.22s/it]
2%|███▍ | 399/17440 [49:31<21:14:28, 4.49s/it]
3%|████▏ | 499/17440 [1:01:50<20:45:51, 4.41s/it]
3%|█████ | 600/17440 [1:14:19<19:27:18, 4.16s/it]
4%|█████▉ | 700/17440 [1:27:12<19:52:48, 4.28s/it]
5%|██████▊ | 799/17440 [1:39:39<20:49:39, 4.51s/it]
5%|███████▋ | 899/17440 [1:52:23<21:09:25, 4.60s/it]
6%|████████▍ | 999/17440 [2:05:08<20:53:06, 4.57s/it]
6%|████████▍ | 1000/17440 [2:05:11<19:26:40, 4.26s/it]The following columns in the evaluation set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length. If input_length are not expected by `Wav2Vec2ForCTC.forward`, you can safely ignore this message.
***** Running Evaluation *****
Num examples = 16021
Batch size = 16
Configuration saved in ./checkpoint-1000/config.json
{'eval_loss': inf, 'eval_wer': 0.9997048122028068, 'eval_runtime': 711.5482, 'eval_samples_per_second': 22.516, 'eval_steps_per_second': 1.408, 'epoch': 0.29}
Model weights saved in ./checkpoint-1000/pytorch_model.bin
Configuration saved in ./checkpoint-1000/preprocessor_config.json