rohitp1 commited on
Commit
357e790
1 Parent(s): cbde93e

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +69 -0
README.md ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - wer
7
+ model-index:
8
+ - name: workstation_whisper_base_finetune_teacher__babble_noise_mozilla_100_epochs_batch_4
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # workstation_whisper_base_finetune_teacher__babble_noise_mozilla_100_epochs_batch_4
16
+
17
+ This model is a fine-tuned version of [openai/whisper-base.en](https://huggingface.co/openai/whisper-base.en) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.3964
20
+ - Wer: 36.5051
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 5e-05
40
+ - train_batch_size: 4
41
+ - eval_batch_size: 1
42
+ - seed: 42
43
+ - gradient_accumulation_steps: 256
44
+ - total_train_batch_size: 1024
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: cosine_with_restarts
47
+ - lr_scheduler_warmup_ratio: 0.2
48
+ - num_epochs: 100
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
54
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|
55
+ | 1.0214 | 7.35 | 500 | 0.8448 | 36.1291 |
56
+ | 0.3301 | 14.7 | 1000 | 0.9065 | 35.5511 |
57
+ | 0.0745 | 22.06 | 1500 | 1.1071 | 36.1535 |
58
+ | 0.0089 | 29.41 | 2000 | 1.2245 | 36.1082 |
59
+ | 0.0026 | 36.76 | 2500 | 1.3039 | 36.3171 |
60
+ | 0.0015 | 44.12 | 3000 | 1.3551 | 36.4216 |
61
+ | 0.001 | 51.47 | 3500 | 1.3964 | 36.5051 |
62
+
63
+
64
+ ### Framework versions
65
+
66
+ - Transformers 4.24.0
67
+ - Pytorch 1.12.1
68
+ - Datasets 2.7.1
69
+ - Tokenizers 0.11.0