Hugging Face's logo

MelanieKoe
/
w2v2-base-pretrained_lr1e-4_at0.8_da0.4

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
MelanieKoe commited on
Commit
3d4c30d
•
1 Parent(s): 052f316

Model save

Browse files
Files changed (2) hide show
  1. README.md +19 -9
  2. model.safetensors +1 -1
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.2246
21
- - Wer: 0.2832
22
 
23
  ## Model description
24
 
@@ -44,17 +44,27 @@ 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: 1000
47
- - num_epochs: 60
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss | Wer |
53
- |:-------------:|:-----:|:----:|:---------------:|:------:|
54
- | 16.9 | 13.16 | 250 | 3.5735 | 1.0 |
55
- | 3.1652 | 26.32 | 500 | 3.1721 | 1.0 |
56
- | 2.4001 | 39.47 | 750 | 1.1944 | 0.7189 |
57
- | 0.2059 | 52.63 | 1000 | 1.2246 | 0.2832 |
 
 
 
 
 
 
 
 
 
 
58
 
59
 
60
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 2.1115
21
+ - Wer: 0.1952
22
 
23
  ## Model description
24
 
 
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 1000
47
+ - training_steps: 3500
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
53
+ |:-------------:|:------:|:----:|:---------------:|:------:|
54
+ | 21.2157 | 13.16 | 250 | 4.1634 | 1.0 |
55
+ | 3.2337 | 26.32 | 500 | 3.1231 | 1.0 |
56
+ | 3.0575 | 39.47 | 750 | 3.0466 | 1.0 |
57
+ | 2.0739 | 52.63 | 1000 | 1.0677 | 0.6284 |
58
+ | 0.1758 | 65.79 | 1250 | 1.3711 | 0.3170 |
59
+ | 0.0675 | 78.95 | 1500 | 1.6521 | 0.2268 |
60
+ | 0.0355 | 92.11 | 1750 | 1.7313 | 0.2332 |
61
+ | 0.0209 | 105.26 | 2000 | 1.9720 | 0.2114 |
62
+ | 0.0162 | 118.42 | 2250 | 1.7569 | 0.2085 |
63
+ | 0.0099 | 131.58 | 2500 | 2.1623 | 0.1944 |
64
+ | 0.0071 | 144.74 | 2750 | 2.2067 | 0.1922 |
65
+ | 0.0066 | 157.89 | 3000 | 2.1246 | 0.1944 |
66
+ | 0.0059 | 171.05 | 3250 | 2.1484 | 0.1922 |
67
+ | 0.0045 | 184.21 | 3500 | 2.1115 | 0.1952 |
68
 
69
 
70
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90fa0b55f40f71a42dc3735e5f4bfce1e4231da4c4e6e9a4376e85da8843ba5a
3
  size 377629528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f1541cd48a917482fdafd83de8586a3e4b554071ff6965fb6f32a5dfb679d5d
3
  size 377629528