kingabzpro commited on
Commit
e2bbfae
1 Parent(s): ea3b802

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +31 -59
README.md CHANGED
@@ -1,57 +1,12 @@
1
  ---
2
- language:
3
- - sv-SE
4
-
5
  license: apache-2.0
6
  tags:
7
- - automatic-speech-recognition
8
- - robust-speech-event
9
  datasets:
10
- - mozilla-foundation/common_voice_8_0
11
- metrics:
12
- - wer
13
- - cer
14
  model-index:
15
- - name: wav2vec2-xls-r-300m-swedish
16
- results:
17
- - task:
18
- type: automatic-speech-recognition # Required. Example: automatic-speech-recognition
19
- name: Speech Recognition # Optional. Example: Speech Recognition
20
- dataset:
21
- type: mozilla-foundation/common_voice_8_0 # Required. Example: common_voice. Use dataset id from https://hf.co/datasets
22
- name: Common Voice sv-SE # Required. Example: Common Voice zh-CN
23
- args: sv-SE # Optional. Example: zh-CN
24
- metrics:
25
- - type: wer # Required. Example: wer
26
- value: 38.57 # Required. Example: 20.90
27
- name: Test WER # Optional. Example: Test WER
28
- args:
29
- - learning_rate: 0.0003
30
- - train_batch_size: 64
31
- - eval_batch_size: 8
32
- - seed: 42
33
- - gradient_accumulation_steps: 2
34
- - total_train_batch_size: 128
35
- - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
36
- - lr_scheduler_type: linear
37
- - lr_scheduler_warmup_steps: 1000
38
- - num_epochs: 30
39
- - mixed_precision_training: Native AMP # Optional. Example for BLEU: max_order
40
- - type: cer # Required. Example: wer
41
- value: 10.98 # Required. Example: 20.90
42
- name: Test CER # Optional. Example: Test WER
43
- args:
44
- - learning_rate: 0.0003
45
- - train_batch_size: 64
46
- - eval_batch_size: 8
47
- - seed: 42
48
- - gradient_accumulation_steps: 2
49
- - total_train_batch_size: 128
50
- - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
- - lr_scheduler_type: linear
52
- - lr_scheduler_warmup_steps: 1000
53
- - num_epochs: 30
54
- - mixed_precision_training: Native AMP # Optional. Example for BLEU: max_order
55
  ---
56
 
57
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -61,15 +16,28 @@ should probably proofread and complete it, then remove this comment. -->
61
 
62
  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 dataset.
63
  It achieves the following results on the evaluation set:
64
- - Loss: 0.4286
65
- - Wer: 0.2729
66
- - Cer: 0.0858
 
 
 
 
 
 
 
 
 
 
 
 
67
 
 
68
 
69
  ### Training hyperparameters
70
 
71
  The following hyperparameters were used during training:
72
- - learning_rate: 0.0003
73
  - train_batch_size: 64
74
  - eval_batch_size: 8
75
  - seed: 42
@@ -78,18 +46,22 @@ The following hyperparameters were used during training:
78
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
79
  - lr_scheduler_type: linear
80
  - lr_scheduler_warmup_steps: 1000
81
- - num_epochs: 30
82
  - mixed_precision_training: Native AMP
83
 
84
  ### Training results
85
 
86
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
87
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
88
- | 4.6203 | 5.49 | 500 | 2.8904 | 1.0 | 1.0 |
89
- | 1.147 | 10.98 | 1000 | 0.5255 | 0.4107 | 0.1304 |
90
- | 0.5246 | 16.48 | 1500 | 0.4598 | 0.3342 | 0.1058 |
91
- | 0.378 | 21.97 | 2000 | 0.4316 | 0.2991 | 0.0949 |
92
- | 0.298 | 27.47 | 2500 | 0.4286 | 0.2729 | 0.0858 |
 
 
 
 
93
 
94
 
95
  ### Framework versions
 
1
  ---
 
 
 
2
  license: apache-2.0
3
  tags:
4
+ - generated_from_trainer
 
5
  datasets:
6
+ - common_voice
 
 
 
7
  model-index:
8
+ - name: wav2vec2-large-xls-r-300m-Swedish
9
+ results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  ---
11
 
12
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
16
 
17
  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 dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.3641
20
+ - Wer: 0.2473
21
+ - Cer: 0.0758
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
 
35
+ ## Training procedure
36
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 7.5e-05
41
  - train_batch_size: 64
42
  - eval_batch_size: 8
43
  - seed: 42
 
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_steps: 1000
49
+ - num_epochs: 50
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
55
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
56
+ | 6.1097 | 5.49 | 500 | 3.1422 | 1.0 | 1.0 |
57
+ | 2.985 | 10.98 | 1000 | 1.7357 | 0.9876 | 0.4125 |
58
+ | 1.0363 | 16.48 | 1500 | 0.4773 | 0.3510 | 0.1047 |
59
+ | 0.6111 | 21.97 | 2000 | 0.3937 | 0.2998 | 0.0910 |
60
+ | 0.4942 | 27.47 | 2500 | 0.3779 | 0.2776 | 0.0844 |
61
+ | 0.4421 | 32.96 | 3000 | 0.3745 | 0.2630 | 0.0807 |
62
+ | 0.4018 | 38.46 | 3500 | 0.3685 | 0.2553 | 0.0781 |
63
+ | 0.3759 | 43.95 | 4000 | 0.3618 | 0.2488 | 0.0761 |
64
+ | 0.3646 | 49.45 | 4500 | 0.3641 | 0.2473 | 0.0758 |
65
 
66
 
67
  ### Framework versions