qmeeus commited on
Commit
7cdbf95
1 Parent(s): 195c991

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -3
README.md CHANGED
@@ -17,8 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the [CGN dataset](https://taalmaterialen.ivdnt.org/download/tstc-corpus-gesproken-nederlands/).
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.3777
21
- - Wer: 19.8814
22
 
23
  ## Model description
24
 
@@ -44,7 +43,7 @@ The following hyperparameters were used during training:
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 50
47
- - training_steps: 1000
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
@@ -61,6 +60,11 @@ The following hyperparameters were used during training:
61
  | 0.6066 | 0.8 | 800 | 0.3804 | 19.2748 |
62
  | 0.2075 | 1.09 | 900 | 0.3794 | 18.8904 |
63
  | 0.2102 | 1.19 | 1000 | 0.3777 | 19.8814 |
 
 
 
 
 
64
 
65
 
66
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the [CGN dataset](https://taalmaterialen.ivdnt.org/download/tstc-corpus-gesproken-nederlands/).
19
  It achieves the following results on the evaluation set:
20
+ - Wer: 15.8367
 
21
 
22
  ## Model description
23
 
 
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
  - lr_scheduler_warmup_steps: 50
46
+ - training_steps: 6000
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
 
60
  | 0.6066 | 0.8 | 800 | 0.3804 | 19.2748 |
61
  | 0.2075 | 1.09 | 900 | 0.3794 | 18.8904 |
62
  | 0.2102 | 1.19 | 1000 | 0.3777 | 19.8814 |
63
+ | 0.2045 | 2.49 | 2000 | 0.3194 | 16.1628 |
64
+ | 0.0652 | 4.97 | 3000 | 0.3425 | 16.3672 |
65
+ | 0.0167 | 7.46 | 4000 | 0.3915 | 15.8187 |
66
+ | 0.0064 | 9.95 | 5000 | 0.4190 | 15.7298 |
67
+ | 0.0041 | 12.44 | 6000 | 0.4315 | 15.8367 |
68
 
69
 
70
  ### Framework versions