mouseyy commited on
Commit
098f399
·
verified ·
1 Parent(s): a08e0ae

Model save

Browse files
Files changed (3) hide show
  1. README.md +29 -1
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -6,9 +6,24 @@ tags:
6
  - generated_from_trainer
7
  datasets:
8
  - common_voice_17_0
 
 
9
  model-index:
10
  - name: best_model_copy
11
- results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  ---
13
 
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,6 +32,10 @@ should probably proofread and complete it, then remove this comment. -->
17
  # best_model_copy
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_17_0 dataset.
 
 
 
 
20
 
21
  ## Model description
22
 
@@ -50,6 +69,15 @@ The following hyperparameters were used during training:
50
 
51
  ### Training results
52
 
 
 
 
 
 
 
 
 
 
53
 
54
 
55
  ### Framework versions
 
6
  - generated_from_trainer
7
  datasets:
8
  - common_voice_17_0
9
+ metrics:
10
+ - wer
11
  model-index:
12
  - name: best_model_copy
13
+ results:
14
+ - task:
15
+ name: Automatic Speech Recognition
16
+ type: automatic-speech-recognition
17
+ dataset:
18
+ name: common_voice_17_0
19
+ type: common_voice_17_0
20
+ config: uk
21
+ split: test
22
+ args: uk
23
+ metrics:
24
+ - name: Wer
25
+ type: wer
26
+ value: 0.3637135578828191
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
  # best_model_copy
33
 
34
  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_17_0 dataset.
35
+ It achieves the following results on the evaluation set:
36
+ - Cer: 0.1700
37
+ - Loss: 0.2233
38
+ - Wer: 0.3637
39
 
40
  ## Model description
41
 
 
69
 
70
  ### Training results
71
 
72
+ | Training Loss | Epoch | Step | Cer | Validation Loss | Wer |
73
+ |:-------------:|:------:|:----:|:------:|:---------------:|:------:|
74
+ | 0.6324 | 0.9099 | 1000 | 0.2381 | 0.5004 | 0.6083 |
75
+ | 0.3497 | 1.8198 | 2000 | 0.1965 | 0.3087 | 0.4650 |
76
+ | 0.2642 | 2.7298 | 3000 | 0.1841 | 0.2636 | 0.4249 |
77
+ | 0.2328 | 3.6397 | 4000 | 0.1789 | 0.2431 | 0.3960 |
78
+ | 0.1933 | 4.5496 | 5000 | 0.1732 | 0.2289 | 0.3773 |
79
+ | 0.1783 | 5.4595 | 6000 | 0.1711 | 0.2300 | 0.3728 |
80
+ | 0.1617 | 6.3694 | 7000 | 0.1700 | 0.2233 | 0.3637 |
81
 
82
 
83
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c140e98e471787fea4b8f014514167fcf0836cc54f031c1e5b597f3fc88d79a9
3
  size 1261971480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6f8e64ea18b595ee8f21b8c07d13549847769d1bc7da3b22438585257a6f9cb
3
  size 1261971480
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d06d4c43237644fa8843b9159fa54e0af1206b1470713744f05cad000c04433
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33279f6708e463d4b31ecca0b0f88bdf01c1016944c5e534c1c3c04214798bb8
3
  size 5432