Hugging Face's logo

EzraWilliam
/
wav2vec2-xlsr-53-CV-demo-google-colab-Ezra_William_Prod18

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
EzraWilliam commited on
Commit
ea6df9c
•
1 Parent(s): f1db368

End of training

Browse files
Files changed (3) hide show
  1. README.md +9 -9
  2. model.safetensors +1 -1
  3. runs/Apr27_11-04-28_48adb50f7d17/events.out.tfevents.1714219845.48adb50f7d17.1124.1 +2 -2
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Wer
24
  type: wer
25
- value: 0.4514657079646018
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the common_voice_13_0 dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.4410
36
- - Wer: 0.4515
37
 
38
  ## Model description
39
 
@@ -65,12 +65,12 @@ The following hyperparameters were used during training:
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Wer |
67
  |:-------------:|:-----:|:----:|:---------------:|:------:|
68
- | 2.9144 | 1.0 | 278 | 2.8244 | 1.0 |
69
- | 0.8558 | 2.0 | 556 | 0.6649 | 0.6956 |
70
- | 0.4993 | 3.0 | 834 | 0.4831 | 0.5467 |
71
- | 0.3655 | 4.0 | 1112 | 0.4493 | 0.4805 |
72
- | 0.291 | 5.0 | 1390 | 0.4419 | 0.4592 |
73
- | 0.2475 | 6.0 | 1668 | 0.4410 | 0.4515 |
74
 
75
 
76
  ### Framework versions
 
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 0.38002396755162243
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the common_voice_13_0 dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.4423
36
+ - Wer: 0.3800
37
 
38
  ## Model description
39
 
 
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Wer |
67
  |:-------------:|:-----:|:----:|:---------------:|:------:|
68
+ | 0.2865 | 1.0 | 278 | 0.4681 | 0.4721 |
69
+ | 0.2346 | 2.0 | 556 | 0.4505 | 0.4318 |
70
+ | 0.1898 | 3.0 | 834 | 0.4389 | 0.4084 |
71
+ | 0.1606 | 4.0 | 1112 | 0.4209 | 0.3981 |
72
+ | 0.1412 | 5.0 | 1390 | 0.4448 | 0.3856 |
73
+ | 0.134 | 6.0 | 1668 | 0.4423 | 0.3800 |
74
 
75
 
76
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:552aa0167ebe92f423f631219d4df576494b2b12d91b52640d30e23d4983520e
3
  size 1261991980
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73151bcab9cc56db48aa195d0ff7b8288f64eea191aa327e1ef98628e4c2699e
3
  size 1261991980
runs/Apr27_11-04-28_48adb50f7d17/events.out.tfevents.1714219845.48adb50f7d17.1124.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2dfc735f4199afc21b584645b65d9920e6e26e8b499377bcb28f4252bc489473
3
- size 11233
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c6f4362c8e659aca88f7e767ae170dc2cb560ecba2e208f382aefb1b9607eea
3
+ size 12116