deepdml commited on
Commit
ae97ecf
1 Parent(s): af7b6c0

End of training

Browse files
Files changed (1) hide show
  1. README.md +82 -0
README.md ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - it
4
+ license: apache-2.0
5
+ base_model: openai/whisper-medium
6
+ tags:
7
+ - generated_from_trainer
8
+ datasets:
9
+ - mozilla-foundation/common_voice_17_0
10
+ metrics:
11
+ - wer
12
+ model-index:
13
+ - name: Whisper Medium it
14
+ results:
15
+ - task:
16
+ name: Automatic Speech Recognition
17
+ type: automatic-speech-recognition
18
+ dataset:
19
+ name: Common Voice 17.0
20
+ type: mozilla-foundation/common_voice_17_0
21
+ config: it
22
+ split: test
23
+ args: it
24
+ metrics:
25
+ - name: Wer
26
+ type: wer
27
+ value: 5.709779804285139
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 Medium it
34
+
35
+ This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 17.0 dataset.
36
+ It achieves the following results on the evaluation set:
37
+ - Loss: 0.1462
38
+ - Wer: 5.7098
39
+
40
+ ## Model description
41
+
42
+ More information needed
43
+
44
+ ## Intended uses & limitations
45
+
46
+ More information needed
47
+
48
+ ## Training and evaluation data
49
+
50
+ More information needed
51
+
52
+ ## Training procedure
53
+
54
+ ### Training hyperparameters
55
+
56
+ The following hyperparameters were used during training:
57
+ - learning_rate: 1e-05
58
+ - train_batch_size: 32
59
+ - eval_batch_size: 8
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: 500
64
+ - training_steps: 5000
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
69
+ |:-------------:|:------:|:----:|:---------------:|:------:|
70
+ | 0.1755 | 0.1730 | 1000 | 0.1974 | 8.0595 |
71
+ | 0.157 | 0.3461 | 2000 | 0.1776 | 7.1199 |
72
+ | 0.1287 | 0.5191 | 3000 | 0.1622 | 6.5201 |
73
+ | 0.1287 | 0.6922 | 4000 | 0.1521 | 5.9863 |
74
+ | 0.1168 | 0.8652 | 5000 | 0.1462 | 5.7098 |
75
+
76
+
77
+ ### Framework versions
78
+
79
+ - Transformers 4.42.0.dev0
80
+ - Pytorch 2.3.0+cu121
81
+ - Datasets 2.19.1
82
+ - Tokenizers 0.19.1