p4b commited on
Commit
e86dcd8
1 Parent(s): 5369a4d

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +19 -24
README.md CHANGED
@@ -1,42 +1,38 @@
1
  ---
2
- language:
3
- - lv
4
  license: apache-2.0
5
  tags:
6
- - whisper-event
7
- - hf-asr-leaderboard
8
  - generated_from_trainer
9
  datasets:
10
- - mozilla-foundation/common_voice_11_0
11
  metrics:
12
  - wer
13
  model-index:
14
- - name: Whisper Large-v2 Latvian
15
  results:
16
  - task:
17
  name: Automatic Speech Recognition
18
  type: automatic-speech-recognition
19
  dataset:
20
- name: mozilla-foundation/common_voice_11_0 lv
21
- type: mozilla-foundation/common_voice_11_0
22
  config: lv
23
  split: test
24
  args: lv
25
  metrics:
26
  - name: Wer
27
  type: wer
28
- value: 27.47628083491461
29
  ---
30
 
31
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
32
  should probably proofread and complete it, then remove this comment. -->
33
 
34
- # Whisper Large-v2 Latvian
35
 
36
- This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the mozilla-foundation/common_voice_11_0 lv dataset.
37
  It achieves the following results on the evaluation set:
38
- - Loss: 0.3179
39
- - Wer: 27.4763
40
 
41
  ## Model description
42
 
@@ -55,27 +51,26 @@ More information needed
55
  ### Training hyperparameters
56
 
57
  The following hyperparameters were used during training:
58
- - learning_rate: 3e-07
59
- - train_batch_size: 64
60
  - eval_batch_size: 32
61
  - seed: 42
62
  - distributed_type: multi-GPU
 
 
63
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
64
  - lr_scheduler_type: cosine
65
- - lr_scheduler_warmup_steps: 200
66
- - training_steps: 1500
67
 
68
  ### Training results
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Wer |
71
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
72
- | 0.5148 | 3.01 | 200 | 0.4189 | 39.3454 |
73
- | 0.3041 | 6.03 | 400 | 0.3335 | 29.5731 |
74
- | 0.1961 | 9.04 | 600 | 0.3186 | 27.7799 |
75
- | 0.2579 | 13.01 | 800 | 0.3167 | 27.5712 |
76
- | 0.2034 | 16.03 | 1000 | 0.3179 | 27.4763 |
77
- | 0.1478 | 19.04 | 1200 | 0.3193 | 27.5237 |
78
- | 0.2169 | 23.01 | 1400 | 0.3198 | 27.5047 |
79
 
80
 
81
  ### Framework versions
 
1
  ---
 
 
2
  license: apache-2.0
3
  tags:
 
 
4
  - generated_from_trainer
5
  datasets:
6
+ - common_voice_11_0
7
  metrics:
8
  - wer
9
  model-index:
10
+ - name: p4b/whisper-large-v2-lv
11
  results:
12
  - task:
13
  name: Automatic Speech Recognition
14
  type: automatic-speech-recognition
15
  dataset:
16
+ name: common_voice_11_0
17
+ type: common_voice_11_0
18
  config: lv
19
  split: test
20
  args: lv
21
  metrics:
22
  - name: Wer
23
  type: wer
24
+ value: 19.97153700189753
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
  should probably proofread and complete it, then remove this comment. -->
29
 
30
+ # p4b/whisper-large-v2-lv
31
 
32
+ This model is a fine-tuned version of [p4b/whisper-large-v2-lv](https://huggingface.co/p4b/whisper-large-v2-lv) on the common_voice_11_0 dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 0.2593
35
+ - Wer: 19.9715
36
 
37
  ## Model description
38
 
 
51
  ### Training hyperparameters
52
 
53
  The following hyperparameters were used during training:
54
+ - learning_rate: 1e-07
55
+ - train_batch_size: 32
56
  - eval_batch_size: 32
57
  - seed: 42
58
  - distributed_type: multi-GPU
59
+ - gradient_accumulation_steps: 2
60
+ - total_train_batch_size: 64
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: cosine
63
+ - lr_scheduler_warmup_steps: 100
64
+ - training_steps: 900
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer |
69
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
70
+ | 0.7919 | 3.03 | 200 | 0.2793 | 22.5806 |
71
+ | 0.4409 | 6.05 | 400 | 0.2651 | 20.6072 |
72
+ | 0.4393 | 10.01 | 600 | 0.2600 | 20.0664 |
73
+ | 0.4975 | 13.04 | 800 | 0.2593 | 19.9715 |
 
 
 
74
 
75
 
76
  ### Framework versions