Hugging Face's logo

catactivationsound
/
whisper-tiny-minds14

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Cat Activation Sound commited on
Commit
d2e2114
•
1 Parent(s): f3b396e

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +98 -0
README.md ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: openai/whisper-tiny
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - PolyAI/minds14
8
+ metrics:
9
+ - wer
10
+ model-index:
11
+ - name: whisper-tiny-minds14
12
+ results:
13
+ - task:
14
+ name: Automatic Speech Recognition
15
+ type: automatic-speech-recognition
16
+ dataset:
17
+ name: PolyAI/minds14
18
+ type: PolyAI/minds14
19
+ config: en-US
20
+ split: train[450:]
21
+ args: en-US
22
+ metrics:
23
+ - name: Wer
24
+ type: wer
25
+ value: 0.2833530106257379
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # whisper-tiny-minds14
32
+
33
+ This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.7473
36
+ - Wer Ortho: 0.2788
37
+ - Wer: 0.2834
38
+
39
+ ## Model description
40
+
41
+ More information needed
42
+
43
+ ## Intended uses & limitations
44
+
45
+ More information needed
46
+
47
+ ## Training and evaluation data
48
+
49
+ More information needed
50
+
51
+ ## Training procedure
52
+
53
+ ### Training hyperparameters
54
+
55
+ The following hyperparameters were used during training:
56
+ - learning_rate: 3.220378398329722e-05
57
+ - train_batch_size: 16
58
+ - eval_batch_size: 64
59
+ - seed: 42
60
+ - optimizer: Adam with betas=(0.9850038588304092,0.9902432649395926) and epsilon=1e-08
61
+ - lr_scheduler_type: linear
62
+ - lr_scheduler_warmup_steps: 205
63
+ - num_epochs: 100
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
68
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
69
+ | No log | 1.0 | 28 | 2.9124 | 0.5305 | 0.3991 |
70
+ | No log | 2.0 | 56 | 1.3721 | 0.4516 | 0.4091 |
71
+ | No log | 3.0 | 84 | 0.6397 | 0.3856 | 0.3872 |
72
+ | No log | 4.0 | 112 | 0.5424 | 0.3849 | 0.3819 |
73
+ | No log | 5.0 | 140 | 0.5124 | 0.4460 | 0.4410 |
74
+ | No log | 6.0 | 168 | 0.5153 | 0.3479 | 0.3477 |
75
+ | No log | 7.0 | 196 | 0.5565 | 0.3418 | 0.3424 |
76
+ | No log | 8.0 | 224 | 0.5882 | 0.3208 | 0.3229 |
77
+ | No log | 9.0 | 252 | 0.6248 | 0.3356 | 0.3371 |
78
+ | No log | 10.0 | 280 | 0.6545 | 0.3282 | 0.3300 |
79
+ | No log | 11.0 | 308 | 0.7122 | 0.3060 | 0.3093 |
80
+ | No log | 12.0 | 336 | 0.7473 | 0.2788 | 0.2834 |
81
+ | No log | 13.0 | 364 | 0.7717 | 0.3072 | 0.3093 |
82
+ | No log | 14.0 | 392 | 0.7852 | 0.3424 | 0.3447 |
83
+ | No log | 15.0 | 420 | 0.8127 | 0.3307 | 0.3318 |
84
+ | No log | 16.0 | 448 | 0.8471 | 0.3300 | 0.3294 |
85
+ | No log | 17.0 | 476 | 0.8614 | 0.3405 | 0.3406 |
86
+ | 0.4338 | 18.0 | 504 | 0.8992 | 0.3627 | 0.3630 |
87
+ | 0.4338 | 19.0 | 532 | 0.9157 | 0.3640 | 0.3648 |
88
+ | 0.4338 | 20.0 | 560 | 0.9274 | 0.3578 | 0.3589 |
89
+ | 0.4338 | 21.0 | 588 | 0.9275 | 0.3387 | 0.3377 |
90
+ | 0.4338 | 22.0 | 616 | 0.9371 | 0.3381 | 0.3371 |
91
+
92
+
93
+ ### Framework versions
94
+
95
+ - Transformers 4.32.0.dev0
96
+ - Pytorch 2.0.1
97
+ - Datasets 2.13.2.dev1
98
+ - Tokenizers 0.13.3