RamNaamSatyaHai commited on
Commit
0dcdbe7
1 Parent(s): 048fe8e

End of training

Browse files
Files changed (3) hide show
  1. README.md +86 -0
  2. generation_config.json +12 -0
  3. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - hi
4
+ license: apache-2.0
5
+ base_model: openai/whisper-small
6
+ tags:
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 Small Hi gpu
15
+ results:
16
+ - task:
17
+ name: Automatic Speech Recognition
18
+ type: automatic-speech-recognition
19
+ dataset:
20
+ name: Common Voice 11.0
21
+ type: mozilla-foundation/common_voice_11_0
22
+ config: hi
23
+ split: test
24
+ args: 'config: hi, split: test'
25
+ metrics:
26
+ - name: Wer
27
+ type: wer
28
+ value: 194.9420130364852
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 Small Hi gpu
35
+
36
+ This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
37
+ It achieves the following results on the evaluation set:
38
+ - Loss: 2.8500
39
+ - Wer: 194.9420
40
+
41
+ ## Model description
42
+
43
+ More information needed
44
+
45
+ ## Intended uses & limitations
46
+
47
+ More information needed
48
+
49
+ ## Training and evaluation data
50
+
51
+ More information needed
52
+
53
+ ## Training procedure
54
+
55
+ ### Training hyperparameters
56
+
57
+ The following hyperparameters were used during training:
58
+ - learning_rate: 1e-05
59
+ - train_batch_size: 32
60
+ - eval_batch_size: 16
61
+ - seed: 42
62
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
+ - lr_scheduler_type: linear
64
+ - lr_scheduler_warmup_steps: 500
65
+ - training_steps: 4000
66
+
67
+ ### Training results
68
+
69
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
70
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
71
+ | 8.6847 | 2.44 | 500 | 8.6186 | 184.5213 |
72
+ | 7.0074 | 4.88 | 1000 | 6.9394 | 502.2010 |
73
+ | 5.0316 | 7.32 | 1500 | 4.9749 | 693.9939 |
74
+ | 3.7844 | 9.76 | 2000 | 3.7445 | 447.2488 |
75
+ | 3.2504 | 12.2 | 2500 | 3.2245 | 326.1619 |
76
+ | 3.0134 | 14.63 | 3000 | 2.9979 | 217.9463 |
77
+ | 2.8995 | 17.07 | 3500 | 2.8893 | 213.6164 |
78
+ | 2.8678 | 19.51 | 4000 | 2.8500 | 194.9420 |
79
+
80
+
81
+ ### Framework versions
82
+
83
+ - Transformers 4.33.1
84
+ - Pytorch 2.0.1+rocm5.4.2
85
+ - Datasets 2.14.5
86
+ - Tokenizers 0.12.1
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "begin_suppress_tokens": [
3
+ 220,
4
+ 50256
5
+ ],
6
+ "bos_token_id": 50256,
7
+ "decoder_start_token_id": 50257,
8
+ "eos_token_id": 50256,
9
+ "pad_token_id": 50256,
10
+ "return_timestamps": false,
11
+ "transformers_version": "4.33.1"
12
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6100d6d557adcdf3bac8a0e3ad17237a678c84966bd387cdd911c3f78039c52
3
  size 113048417
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d5b0c8de1717e1ed726fb3187e8eb1613980565a85666952f553c298e71545e
3
  size 113048417