Hugging Face's logo

mattiasu96
/
whisper-tiny-it

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Italian
whisper
whisper-event
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
2
mattiasu96 commited on
Commit
17c7ba1
•
1 Parent(s): bd387ee

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +18 -21
README.md CHANGED
@@ -1,41 +1,38 @@
1
  ---
2
- language:
3
- - it
4
  license: apache-2.0
5
  tags:
6
- - whisper-event
7
  - generated_from_trainer
8
  datasets:
9
- - mozilla-foundation/common_voice_11_0
10
  metrics:
11
  - wer
12
  model-index:
13
- - name: Whisper tiny Italian - Mattia Surricchio
14
  results:
15
  - task:
16
  name: Automatic Speech Recognition
17
  type: automatic-speech-recognition
18
  dataset:
19
- name: Common Voice 11.0
20
- type: mozilla-foundation/common_voice_11_0
21
  config: it
22
  split: test
23
  args: it
24
  metrics:
25
  - name: Wer
26
  type: wer
27
- value: 38.08739102700404
28
  ---
29
 
30
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
31
  should probably proofread and complete it, then remove this comment. -->
32
 
33
- # Whisper tiny Italian - Mattia Surricchio
34
 
35
- This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Common Voice 11.0 dataset.
36
  It achieves the following results on the evaluation set:
37
- - Loss: 0.6699
38
- - Wer: 38.0874
39
 
40
  ## Model description
41
 
@@ -60,24 +57,24 @@ The following hyperparameters were used during training:
60
  - seed: 42
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
- - lr_scheduler_warmup_steps: 100
64
- - training_steps: 500
65
  - mixed_precision_training: Native AMP
66
 
67
  ### Training results
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Wer |
70
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
71
- | 0.9004 | 0.2 | 100 | 0.8327 | 44.9534 |
72
- | 0.6534 | 0.4 | 200 | 0.7341 | 41.3160 |
73
- | 0.6727 | 0.6 | 300 | 0.6988 | 39.5871 |
74
- | 0.4996 | 0.8 | 400 | 0.6766 | 38.6582 |
75
- | 0.6236 | 1.0 | 500 | 0.6699 | 38.0874 |
76
 
77
 
78
  ### Framework versions
79
 
80
  - Transformers 4.26.0.dev0
81
- - Pytorch 1.11.0
82
  - Datasets 2.7.1.dev0
83
- - Tokenizers 0.12.1
 
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: openai/whisper-tiny
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: it
19
  split: test
20
  args: it
21
  metrics:
22
  - name: Wer
23
  type: wer
24
+ value: 26.495056347012547
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
+ # openai/whisper-tiny
31
 
32
+ This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the common_voice_11_0 dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 0.4736
35
+ - Wer: 26.4951
36
 
37
  ## Model description
38
 
 
57
  - seed: 42
58
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
  - lr_scheduler_type: linear
60
+ - lr_scheduler_warmup_steps: 500
61
+ - training_steps: 5000
62
  - mixed_precision_training: Native AMP
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Wer |
67
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
68
+ | 0.3889 | 0.2 | 1000 | 0.6844 | 39.1000 |
69
+ | 0.5832 | 0.4 | 2000 | 0.5691 | 31.9995 |
70
+ | 0.524 | 0.6 | 3000 | 0.4993 | 28.2672 |
71
+ | 0.4663 | 0.8 | 4000 | 0.4799 | 26.7230 |
72
+ | 0.3107 | 1.05 | 5000 | 0.4736 | 26.4951 |
73
 
74
 
75
  ### Framework versions
76
 
77
  - Transformers 4.26.0.dev0
78
+ - Pytorch 1.12.1+cu113
79
  - Datasets 2.7.1.dev0
80
+ - Tokenizers 0.13.2