proseph commited on
Commit
3aaa391
·
1 Parent(s): 328486c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -2
README.md CHANGED
@@ -12,11 +12,14 @@ should probably proofread and complete it, then remove this comment. -->
12
 
13
  # ctrlv-speechrecognition-model
14
 
15
- This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
  - Loss: 0.4730
18
  - Wer: 0.3031
19
 
 
 
 
20
  ## Model description
21
 
22
  More information needed
@@ -72,4 +75,4 @@ The following hyperparameters were used during training:
72
  - Transformers 4.11.3
73
  - Pytorch 1.10.0+cu111
74
  - Datasets 1.18.3
75
- - Tokenizers 0.10.3
 
12
 
13
  # ctrlv-speechrecognition-model
14
 
15
+ This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the TIMIT dataset.
16
  It achieves the following results on the evaluation set:
17
  - Loss: 0.4730
18
  - Wer: 0.3031
19
 
20
+ ## Test WER in TIMIT dataset
21
+ - Wer: 0.189
22
+
23
  ## Model description
24
 
25
  More information needed
 
75
  - Transformers 4.11.3
76
  - Pytorch 1.10.0+cu111
77
  - Datasets 1.18.3
78
+ - Tokenizers 0.10.3