diallomama commited on
Commit
f7bebf0
1 Parent(s): 30333b2

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -11
README.md CHANGED
@@ -14,17 +14,15 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # wav2vec2_xlsr
16
 
17
- ## Training was stopped but going to be retrained
18
-
19
- This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset on spanish subset.
20
  It achieves the following results on the evaluation set:
21
- - eval_loss: 0.2546
22
- - eval_wer: 0.9870
23
- - eval_runtime: 918.8309
24
- - eval_samples_per_second: 16.422
25
- - eval_steps_per_second: 2.054
26
- - epoch: 0.63
27
- - step: 3200
28
 
29
  ## Model description
30
 
@@ -52,7 +50,7 @@ The following hyperparameters were used during training:
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
  - lr_scheduler_type: linear
54
  - lr_scheduler_warmup_steps: 500
55
- - num_epochs: 15
56
  - mixed_precision_training: Native AMP
57
 
58
  ### Framework versions
 
14
 
15
  # wav2vec2_xlsr
16
 
17
+ This model is a fine-tuned version of [diallomama/wav2vec2_xlsr](https://huggingface.co/diallomama/wav2vec2_xlsr) on the common_voice dataset.
 
 
18
  It achieves the following results on the evaluation set:
19
+ - eval_loss: 0.2204
20
+ - eval_wer: 0.9719
21
+ - eval_runtime: 923.0808
22
+ - eval_samples_per_second: 16.346
23
+ - eval_steps_per_second: 2.044
24
+ - epoch: 1.66
25
+ - step: 8400
26
 
27
  ## Model description
28
 
 
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
  - lr_scheduler_warmup_steps: 500
53
+ - num_epochs: 10
54
  - mixed_precision_training: Native AMP
55
 
56
  ### Framework versions