Hugging Face's logo

velocity-ai
/
velocity-whisper-hi-tiny

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Hindi
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
velocity-ai commited on
Commit
6332be7
•
1 Parent(s): 39102f0

End of training

Browse files
Files changed (3) hide show
  1. README.md +28 -8
  2. model.safetensors +1 -1
  3. runs/Jun06_12-49-12_cfc43d5a78fd/events.out.tfevents.1717678154.cfc43d5a78fd.1615.0 +2 -2
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Wer
24
  type: wer
25
- value: 10.60473269062226
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the whisper-training dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.0702
36
- - Wer: 10.6047
37
 
38
  ## Model description
39
 
@@ -64,15 +64,35 @@ The following hyperparameters were used during training:
64
 
65
  ### Training results
66
 
67
- | Training Loss | Epoch | Step | Validation Loss | Wer |
68
- |:-------------:|:-------:|:----:|:---------------:|:-------:|
69
- | 0.001 | 17.8571 | 1000 | 0.0647 | 10.4294 |
70
- | 0.0003 | 35.7143 | 2000 | 0.0702 | 10.6047 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
71
 
72
 
73
  ### Framework versions
74
 
75
  - Transformers 4.41.2
76
- - Pytorch 2.3.0+cu121
77
  - Datasets 2.19.2
78
  - Tokenizers 0.19.1
 
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 42.262816735415434
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the whisper-training dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.7758
36
+ - Wer: 42.2628
37
 
38
  ## Model description
39
 
 
64
 
65
  ### Training results
66
 
67
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
68
+ |:-------------:|:-------:|:-----:|:---------------:|:-------:|
69
+ | 0.3632 | 1.7825 | 1000 | 0.3962 | 51.0784 |
70
+ | 0.2411 | 3.5651 | 2000 | 0.3428 | 45.1149 |
71
+ | 0.1242 | 5.3476 | 3000 | 0.3459 | 42.1685 |
72
+ | 0.0813 | 7.1301 | 4000 | 0.3610 | 42.1685 |
73
+ | 0.0654 | 8.9127 | 5000 | 0.3949 | 41.9210 |
74
+ | 0.0309 | 10.6952 | 6000 | 0.4422 | 42.7814 |
75
+ | 0.0161 | 12.4777 | 7000 | 0.4836 | 42.3925 |
76
+ | 0.0067 | 14.2602 | 8000 | 0.5291 | 42.9346 |
77
+ | 0.0032 | 16.0428 | 9000 | 0.5645 | 42.4514 |
78
+ | 0.0031 | 17.8253 | 10000 | 0.5951 | 42.7814 |
79
+ | 0.002 | 19.6078 | 11000 | 0.6248 | 42.5103 |
80
+ | 0.0007 | 21.3904 | 12000 | 0.6486 | 42.8167 |
81
+ | 0.0004 | 23.1729 | 13000 | 0.6760 | 42.0625 |
82
+ | 0.0008 | 24.9554 | 14000 | 0.6982 | 42.4396 |
83
+ | 0.0018 | 26.7380 | 15000 | 0.7149 | 42.4985 |
84
+ | 0.0002 | 28.5205 | 16000 | 0.7172 | 41.8739 |
85
+ | 0.0001 | 30.3030 | 17000 | 0.7307 | 42.4042 |
86
+ | 0.0001 | 32.0856 | 18000 | 0.7399 | 42.0742 |
87
+ | 0.0001 | 33.8681 | 19000 | 0.7497 | 42.1332 |
88
+ | 0.0001 | 35.6506 | 20000 | 0.7608 | 42.0860 |
89
+ | 0.0 | 37.4332 | 21000 | 0.7695 | 41.9682 |
90
+ | 0.0 | 39.2157 | 22000 | 0.7758 | 42.2628 |
91
 
92
 
93
  ### Framework versions
94
 
95
  - Transformers 4.41.2
96
+ - Pytorch 2.3.1+cu121
97
  - Datasets 2.19.2
98
  - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7536d13cac6fbfbcd71783a497c39a6cde38c178863fe016a51efc485dbeeb8b
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1345947138b74e1099022f5a7241d58aee96267fa512ebf28ee243ce61cf6993
3
  size 151061672
runs/Jun06_12-49-12_cfc43d5a78fd/events.out.tfevents.1717678154.cfc43d5a78fd.1615.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:566f714e3053cae59088c41a7e450aaf39f8ea4d5901fd10ec6a05bf8e41ccaa
3
- size 200229
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d395f7e406e38b11a7434127ed1cd7cc7bf3f8e0ff0db86a5f07ca2ae1a8a2d6
3
+ size 204244