Hugging Face's logo

akera
/
whisper-medium-lug

Automatic Speech Recognition
Transformers
Safetensors
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
akera commited on
Commit
7c1f326
·
verified ·
1 Parent(s): 86138f8

Model save

Browse files
Files changed (2) hide show
  1. README.md +68 -2
  2. model.safetensors +1 -1
README.md CHANGED
@@ -3,9 +3,26 @@ license: apache-2.0
3
  base_model: openai/whisper-medium
4
  tags:
5
  - generated_from_trainer
 
 
 
 
6
  model-index:
7
  - name: whisper-medium-lug
8
- results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  ---
10
 
11
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -14,7 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
14
  [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/bakera-sunbird/huggingface/runs/c6s8tlgq)
15
  # whisper-medium-lug
16
 
17
- This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on an unknown dataset.
 
 
 
18
 
19
  ## Model description
20
 
@@ -43,6 +63,52 @@ The following hyperparameters were used during training:
43
  - training_steps: 8000
44
  - mixed_precision_training: Native AMP
45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
46
  ### Framework versions
47
 
48
  - Transformers 4.41.0.dev0
 
3
  base_model: openai/whisper-medium
4
  tags:
5
  - generated_from_trainer
6
+ datasets:
7
+ - generator
8
+ metrics:
9
+ - wer
10
  model-index:
11
  - name: whisper-medium-lug
12
+ results:
13
+ - task:
14
+ name: Automatic Speech Recognition
15
+ type: automatic-speech-recognition
16
+ dataset:
17
+ name: generator
18
+ type: generator
19
+ config: default
20
+ split: train
21
+ args: default
22
+ metrics:
23
+ - name: Wer
24
+ type: wer
25
+ value: 61.62227602905569
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
31
  [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/bakera-sunbird/huggingface/runs/c6s8tlgq)
32
  # whisper-medium-lug
33
 
34
+ This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the generator dataset.
35
+ It achieves the following results on the evaluation set:
36
+ - Loss: 0.2943
37
+ - Wer: 61.6223
38
 
39
  ## Model description
40
 
 
63
  - training_steps: 8000
64
  - mixed_precision_training: Native AMP
65
 
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
69
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|
70
+ | 0.9437 | 0.025 | 200 | 0.4902 | 427.9661 |
71
+ | 0.4586 | 1.0108 | 400 | 0.3298 | 150.3027 |
72
+ | 0.3741 | 1.0357 | 600 | 0.3337 | 143.5835 |
73
+ | 0.2659 | 2.0215 | 800 | 0.2871 | 109.6852 |
74
+ | 0.139 | 3.0072 | 1000 | 0.3437 | 131.9613 |
75
+ | 0.1734 | 3.0322 | 1200 | 0.3028 | 170.8838 |
76
+ | 0.1072 | 4.018 | 1400 | 0.2943 | 61.6223 |
77
+ | 0.0726 | 5.0038 | 1600 | 0.3438 | 114.7094 |
78
+ | 0.0751 | 5.0287 | 1800 | 0.3526 | 73.6683 |
79
+ | 0.0635 | 6.0145 | 2000 | 0.3629 | 159.7458 |
80
+ | 0.0554 | 7.0003 | 2200 | 0.3854 | 152.1186 |
81
+ | 0.0549 | 7.0252 | 2400 | 0.3751 | 98.5472 |
82
+ | 0.0283 | 8.011 | 2600 | 0.3190 | 89.2857 |
83
+ | 0.0349 | 8.036 | 2800 | 0.3452 | 155.5085 |
84
+ | 0.0379 | 9.0218 | 3000 | 0.3780 | 109.7458 |
85
+ | 0.0316 | 10.0075 | 3200 | 0.3880 | 101.4528 |
86
+ | 0.0232 | 10.0325 | 3400 | 0.4144 | 67.7966 |
87
+ | 0.0246 | 11.0183 | 3600 | 0.3820 | 71.0654 |
88
+ | 0.0192 | 12.004 | 3800 | 0.4022 | 107.6877 |
89
+ | 0.0195 | 12.029 | 4000 | 0.4276 | 126.9976 |
90
+ | 0.013 | 13.0147 | 4200 | 0.4128 | 115.3753 |
91
+ | 0.0154 | 14.0005 | 4400 | 0.4371 | 126.6949 |
92
+ | 0.0109 | 14.0255 | 4600 | 0.4213 | 142.2518 |
93
+ | 0.0133 | 15.0113 | 4800 | 0.4075 | 170.1574 |
94
+ | 0.011 | 15.0363 | 5000 | 0.4454 | 116.1622 |
95
+ | 0.0104 | 16.022 | 5200 | 0.3950 | 79.5400 |
96
+ | 0.0079 | 17.0078 | 5400 | 0.4330 | 109.2010 |
97
+ | 0.0083 | 17.0328 | 5600 | 0.4308 | 137.5303 |
98
+ | 0.0064 | 18.0185 | 5800 | 0.4178 | 96.2470 |
99
+ | 0.0057 | 19.0042 | 6000 | 0.4104 | 99.7579 |
100
+ | 0.0076 | 19.0293 | 6200 | 0.4132 | 117.0702 |
101
+ | 0.0062 | 20.015 | 6400 | 0.4404 | 146.2470 |
102
+ | 0.0035 | 21.0008 | 6600 | 0.4488 | 128.4504 |
103
+ | 0.0045 | 21.0257 | 6800 | 0.4415 | 91.0412 |
104
+ | 0.0043 | 22.0115 | 7000 | 0.4477 | 89.5884 |
105
+ | 0.0038 | 22.0365 | 7200 | 0.4550 | 82.5666 |
106
+ | 0.0028 | 23.0222 | 7400 | 0.4451 | 77.4213 |
107
+ | 0.003 | 24.008 | 7600 | 0.4424 | 78.5109 |
108
+ | 0.0033 | 24.033 | 7800 | 0.4448 | 73.4867 |
109
+ | 0.0041 | 25.0188 | 8000 | 0.4455 | 86.4407 |
110
+
111
+
112
  ### Framework versions
113
 
114
  - Transformers 4.41.0.dev0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44779518de0e3894972a1c6237dcca55c8c0fdb1af6feb88afee1b3871138e01
3
  size 3055544304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff67acf088a5fc822729080521a6ef81d2168c71dfa3ba8292cc473b675efa6f
3
  size 3055544304