Hugging Face's logo

akera
/
whisper-medium-lug-only

Automatic Speech Recognition
Transformers
Safetensors
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
akera commited on
Commit
257133d
•
1 Parent(s): 63b4b3c

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-only
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/rim7iyop)
15
  # whisper-medium-lug-only
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-only
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: 9.766162310866575
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/rim7iyop)
32
  # whisper-medium-lug-only
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: 0.1551
37
+ - Wer: 9.7662
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
+ | 1.1474 | 0.025 | 200 | 0.7380 | 71.3893 |
71
+ | 0.7879 | 0.05 | 400 | 0.4461 | 44.7043 |
72
+ | 0.6541 | 0.075 | 600 | 0.3394 | 32.3246 |
73
+ | 0.5203 | 0.1 | 800 | 0.2949 | 26.5475 |
74
+ | 0.509 | 0.125 | 1000 | 0.2774 | 24.2091 |
75
+ | 0.4753 | 0.15 | 1200 | 0.2505 | 20.4952 |
76
+ | 0.4726 | 0.175 | 1400 | 0.2375 | 20.7703 |
77
+ | 0.4145 | 0.2 | 1600 | 0.2313 | 18.2944 |
78
+ | 0.418 | 0.225 | 1800 | 0.2265 | 18.8446 |
79
+ | 0.4032 | 0.25 | 2000 | 0.2267 | 18.7070 |
80
+ | 0.3797 | 0.275 | 2200 | 0.2184 | 16.2311 |
81
+ | 0.3773 | 0.3 | 2400 | 0.2084 | 14.4429 |
82
+ | 0.3497 | 0.325 | 2600 | 0.1993 | 15.2682 |
83
+ | 0.3657 | 0.35 | 2800 | 0.1951 | 15.4058 |
84
+ | 0.3686 | 0.375 | 3000 | 0.1882 | 13.2050 |
85
+ | 0.3363 | 0.4 | 3200 | 0.1848 | 14.3054 |
86
+ | 0.3286 | 0.425 | 3400 | 0.1769 | 13.8927 |
87
+ | 0.3193 | 0.45 | 3600 | 0.1786 | 12.5172 |
88
+ | 0.3352 | 0.475 | 3800 | 0.1758 | 11.9670 |
89
+ | 0.3182 | 0.5 | 4000 | 0.1737 | 13.3425 |
90
+ | 0.2967 | 0.525 | 4200 | 0.1699 | 12.9298 |
91
+ | 0.3078 | 0.55 | 4400 | 0.1719 | 12.3796 |
92
+ | 0.2788 | 0.575 | 4600 | 0.1663 | 12.2421 |
93
+ | 0.2302 | 1.0075 | 4800 | 0.1678 | 11.4168 |
94
+ | 0.2109 | 1.0325 | 5000 | 0.1696 | 11.1417 |
95
+ | 0.1932 | 1.0575 | 5200 | 0.1713 | 11.2792 |
96
+ | 0.2128 | 1.0825 | 5400 | 0.1663 | 12.6547 |
97
+ | 0.2269 | 1.1075 | 5600 | 0.1621 | 12.2421 |
98
+ | 0.2324 | 1.1325 | 5800 | 0.1581 | 11.2792 |
99
+ | 0.2083 | 1.1575 | 6000 | 0.1579 | 11.1417 |
100
+ | 0.2156 | 1.1825 | 6200 | 0.1543 | 10.4539 |
101
+ | 0.2113 | 1.2075 | 6400 | 0.1551 | 9.7662 |
102
+ | 0.2235 | 1.2325 | 6600 | 0.1550 | 10.5915 |
103
+ | 0.2137 | 1.2575 | 6800 | 0.1537 | 10.4539 |
104
+ | 0.1989 | 1.2825 | 7000 | 0.1536 | 9.9037 |
105
+ | 0.2014 | 1.3075 | 7200 | 0.1515 | 10.1788 |
106
+ | 0.2109 | 1.3325 | 7400 | 0.1488 | 10.3164 |
107
+ | 0.1975 | 1.3575 | 7600 | 0.1500 | 10.5915 |
108
+ | 0.1754 | 1.3825 | 7800 | 0.1494 | 10.0413 |
109
+ | 0.182 | 1.4075 | 8000 | 0.1487 | 10.0413 |
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 sha256:1d0efe460d4208c8d6f09722a81eb7779f82d56bd83187f33859a5030ac0807d
3
  size 3055544304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f86fbfcd6828860616926b3a339c57357ab9c3823dbb8ad5da8bd4202fe6e3f4
3
  size 3055544304