riteshkr commited on
Commit
61bd783
·
verified ·
1 Parent(s): f6103e8

End of training

Browse files
Files changed (2) hide show
  1. README.md +30 -10
  2. model.safetensors +1 -1
README.md CHANGED
@@ -7,25 +7,35 @@ tags:
7
  - generated_from_trainer
8
  datasets:
9
  - mozilla-foundation/common_voice_11_0
 
 
10
  model-index:
11
- - name: Whisper Small Hi - Sanchit Gandhi
12
- results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  ---
14
 
15
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
  should probably proofread and complete it, then remove this comment. -->
17
 
18
- # Whisper Small Hi - Sanchit Gandhi
19
 
20
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
21
  It achieves the following results on the evaluation set:
22
- - eval_loss: 0.2980
23
- - eval_wer: 35.0250
24
- - eval_runtime: 1303.7894
25
- - eval_samples_per_second: 2.22
26
- - eval_steps_per_second: 0.278
27
- - epoch: 2.4450
28
- - step: 1000
29
 
30
  ## Model description
31
 
@@ -54,6 +64,16 @@ The following hyperparameters were used during training:
54
  - training_steps: 4000
55
  - mixed_precision_training: Native AMP
56
 
 
 
 
 
 
 
 
 
 
 
57
  ### Framework versions
58
 
59
  - Transformers 4.42.4
 
7
  - generated_from_trainer
8
  datasets:
9
  - mozilla-foundation/common_voice_11_0
10
+ metrics:
11
+ - wer
12
  model-index:
13
+ - name: Whisper Small Hi - Ritesh
14
+ results:
15
+ - task:
16
+ name: Automatic Speech Recognition
17
+ type: automatic-speech-recognition
18
+ dataset:
19
+ name: Common Voice 11.0
20
+ type: mozilla-foundation/common_voice_11_0
21
+ config: hi
22
+ split: None
23
+ args: 'config: hi, split: test'
24
+ metrics:
25
+ - name: Wer
26
+ type: wer
27
+ value: 32.56158469482774
28
  ---
29
 
30
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
31
  should probably proofread and complete it, then remove this comment. -->
32
 
33
+ # Whisper Small Hi - Ritesh
34
 
35
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
36
  It achieves the following results on the evaluation set:
37
+ - Loss: 0.4383
38
+ - Wer: 32.5616
 
 
 
 
 
39
 
40
  ## Model description
41
 
 
64
  - training_steps: 4000
65
  - mixed_precision_training: Native AMP
66
 
67
+ ### Training results
68
+
69
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
70
+ |:-------------:|:------:|:----:|:---------------:|:-------:|
71
+ | 0.0917 | 2.4450 | 1000 | 0.2986 | 35.0715 |
72
+ | 0.0213 | 4.8900 | 2000 | 0.3490 | 33.7129 |
73
+ | 0.0013 | 7.3350 | 3000 | 0.4147 | 32.3965 |
74
+ | 0.0005 | 9.7800 | 4000 | 0.4383 | 32.5616 |
75
+
76
+
77
  ### Framework versions
78
 
79
  - Transformers 4.42.4
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0b106df4590f8b700f7effbe1d89a5db305c7e39067942cfd0d31acee7f0536
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a44681b2a69d793980ec3209a75a7743e0b0055826ad8ca3b156c7fa7c38b0d
3
  size 966995080