Hugging Face's logo

LeonM78Code
/
whisper-small-dv

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Divehi
whisper
Generated from Trainer
Eval Results
Model card Files
xet
Metrics Community
LeonM78Code commited on
Commit
a666a42
·
verified ·
1 Parent(s): 7a863a6

End of training

Browse files
Files changed (19) hide show
  1. README.md +19 -17
  2. model.safetensors +1 -1
  3. runs/Apr10_11-15-28_a-System-Product-Name/events.out.tfevents.1744251346.a-System-Product-Name.4377.0 +3 -0
  4. runs/Apr10_11-25-28_a-System-Product-Name/events.out.tfevents.1744251935.a-System-Product-Name.4373.0 +3 -0
  5. runs/Apr10_11-26-43_a-System-Product-Name/events.out.tfevents.1744252007.a-System-Product-Name.4373.1 +3 -0
  6. runs/Apr10_11-32-12_a-System-Product-Name/events.out.tfevents.1744252335.a-System-Product-Name.3942.0 +3 -0
  7. runs/Apr10_11-34-22_a-System-Product-Name/events.out.tfevents.1744252466.a-System-Product-Name.3942.1 +3 -0
  8. runs/Apr10_11-38-12_a-System-Product-Name/events.out.tfevents.1744252696.a-System-Product-Name.3970.0 +3 -0
  9. runs/Apr10_17-24-52_a-System-Product-Name/events.out.tfevents.1744273555.a-System-Product-Name.3865.0 +3 -0
  10. runs/Apr10_18-13-02_a-System-Product-Name/events.out.tfevents.1744276387.a-System-Product-Name.3791.0 +3 -0
  11. runs/Apr10_18-29-52_a-System-Product-Name/events.out.tfevents.1744277396.a-System-Product-Name.3817.0 +3 -0
  12. runs/Apr10_18-34-17_a-System-Product-Name/events.out.tfevents.1744277658.a-System-Product-Name.3732.0 +3 -0
  13. runs/Apr10_18-37-43_a-System-Product-Name/events.out.tfevents.1744277865.a-System-Product-Name.3790.0 +3 -0
  14. runs/Apr10_18-42-36_a-System-Product-Name/events.out.tfevents.1744278158.a-System-Product-Name.3765.0 +3 -0
  15. runs/Apr11_09-37-30_a-System-Product-Name/events.out.tfevents.1744331868.a-System-Product-Name.5092.0 +3 -0
  16. runs/Apr11_16-35-19_a-System-Product-Name/events.out.tfevents.1744356920.a-System-Product-Name.3984.0 +3 -0
  17. runs/Apr11_16-40-58_a-System-Product-Name/events.out.tfevents.1744357261.a-System-Product-Name.3968.0 +3 -0
  18. runs/Apr13_10-24-01_a-System-Product-Name/events.out.tfevents.1744507443.a-System-Product-Name.4115.0 +3 -0
  19. training_args.bin +1 -1
README.md CHANGED
@@ -25,7 +25,7 @@ model-index:
25
  metrics:
26
  - name: Wer
27
  type: wer
28
- value: 11.131202837569983
29
  ---
30
 
31
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -35,9 +35,9 @@ should probably proofread and complete it, then remove this comment. -->
35
 
36
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 13 dataset.
37
  It achieves the following results on the evaluation set:
38
- - Loss: 0.2823
39
- - Wer Ortho: 57.2394
40
- - Wer: 11.1312
41
 
42
  ## Model description
43
 
@@ -56,13 +56,15 @@ More information needed
56
  ### Training hyperparameters
57
 
58
  The following hyperparameters were used during training:
59
- - learning_rate: 1e-05
60
- - train_batch_size: 16
61
- - eval_batch_size: 16
62
  - seed: 42
 
 
63
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
64
- - lr_scheduler_type: constant_with_warmup
65
- - lr_scheduler_warmup_steps: 50
66
  - training_steps: 4000
67
  - mixed_precision_training: Native AMP
68
 
@@ -70,14 +72,14 @@ The following hyperparameters were used during training:
70
 
71
  | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
72
  |:-------------:|:-------:|:----:|:---------------:|:---------:|:-------:|
73
- | 0.1196 | 1.6287 | 500 | 0.1738 | 63.4236 | 13.7480 |
74
- | 0.0452 | 3.2573 | 1000 | 0.1736 | 58.6949 | 11.8249 |
75
- | 0.0304 | 4.8860 | 1500 | 0.1862 | 57.5945 | 11.4233 |
76
- | 0.0117 | 6.5147 | 2000 | 0.2327 | 57.8035 | 11.2964 |
77
- | 0.0059 | 8.1433 | 2500 | 0.2574 | 58.2561 | 11.2825 |
78
- | 0.0059 | 9.7720 | 3000 | 0.2652 | 58.1169 | 11.2216 |
79
- | 0.005 | 11.4007 | 3500 | 0.2835 | 56.7728 | 11.0182 |
80
- | 0.0044 | 13.0293 | 4000 | 0.2823 | 57.2394 | 11.1312 |
81
 
82
 
83
  ### Framework versions
 
25
  metrics:
26
  - name: Wer
27
  type: wer
28
+ value: 9.938449768751955
29
  ---
30
 
31
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
35
 
36
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 13 dataset.
37
  It achieves the following results on the evaluation set:
38
+ - Loss: 0.4909
39
+ - Wer Ortho: 53.6249
40
+ - Wer: 9.9384
41
 
42
  ## Model description
43
 
 
56
  ### Training hyperparameters
57
 
58
  The following hyperparameters were used during training:
59
+ - learning_rate: 5e-05
60
+ - train_batch_size: 32
61
+ - eval_batch_size: 32
62
  - seed: 42
63
+ - gradient_accumulation_steps: 2
64
+ - total_train_batch_size: 64
65
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
66
+ - lr_scheduler_type: linear
67
+ - lr_scheduler_warmup_steps: 100
68
  - training_steps: 4000
69
  - mixed_precision_training: Native AMP
70
 
 
72
 
73
  | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
74
  |:-------------:|:-------:|:----:|:---------------:|:---------:|:-------:|
75
+ | 0.0162 | 6.4935 | 500 | 0.2193 | 57.3020 | 11.4285 |
76
+ | 0.0027 | 12.9870 | 1000 | 0.2799 | 55.4287 | 10.4983 |
77
+ | 0.0013 | 19.4805 | 1500 | 0.3227 | 55.2824 | 10.5105 |
78
+ | 0.0007 | 25.9740 | 2000 | 0.3129 | 54.6069 | 10.4149 |
79
+ | 0.0 | 32.4675 | 2500 | 0.3903 | 53.6249 | 9.9680 |
80
+ | 0.0 | 38.9610 | 3000 | 0.4478 | 53.6945 | 9.9332 |
81
+ | 0.0 | 45.4545 | 3500 | 0.4796 | 53.6458 | 9.9524 |
82
+ | 0.0 | 51.9481 | 4000 | 0.4909 | 53.6249 | 9.9384 |
83
 
84
 
85
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0eb875c3fed70042f5ae5bbb7648d7a3b44cefe8a0fdaeaa530fd4c8de0a40b1
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a2ef571cd07fb6771024a8a94837f6de2a28033789e3f3e229aecdf80f637ce
3
  size 966995080
runs/Apr10_11-15-28_a-System-Product-Name/events.out.tfevents.1744251346.a-System-Product-Name.4377.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8da5be8860f6ef9584f6cc78842145d590e0721006cee2d2cfa03749e46fff4
3
+ size 6826
runs/Apr10_11-25-28_a-System-Product-Name/events.out.tfevents.1744251935.a-System-Product-Name.4373.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3060ed005fcee648dd6c2c70fc4853f50d1ea5ab3caa7f200f4e8e00be66406
3
+ size 6824
runs/Apr10_11-26-43_a-System-Product-Name/events.out.tfevents.1744252007.a-System-Product-Name.4373.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58a152f7d24a233336f01a779054f17f30ee24982097b04ee1314ae970eed764
3
+ size 6824
runs/Apr10_11-32-12_a-System-Product-Name/events.out.tfevents.1744252335.a-System-Product-Name.3942.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20679fd9ce6db25f199bb20ae29ad5b70b9ba6583985dcce2c719507c0b2c9a0
3
+ size 6824
runs/Apr10_11-34-22_a-System-Product-Name/events.out.tfevents.1744252466.a-System-Product-Name.3942.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a05f92ad906150eb7f5cc1add74f95e9ab843470b93ec4b19b83c21e449e1ef9
3
+ size 6824
runs/Apr10_11-38-12_a-System-Product-Name/events.out.tfevents.1744252696.a-System-Product-Name.3970.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6e10da1e55ab80f626b0d26d70b78205d3734e8f6c64d1e17fddf42b575afb4
3
+ size 43886
runs/Apr10_17-24-52_a-System-Product-Name/events.out.tfevents.1744273555.a-System-Product-Name.3865.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f98a1859ef2198592f98983f1f29a418d2961cca564bd385e7392b402b31d0db
3
+ size 10442
runs/Apr10_18-13-02_a-System-Product-Name/events.out.tfevents.1744276387.a-System-Product-Name.3791.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:662b40c61e29e71dfed204ffd316beb729736f571ebdc51fabf4af1034d5b44f
3
+ size 8017
runs/Apr10_18-29-52_a-System-Product-Name/events.out.tfevents.1744277396.a-System-Product-Name.3817.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0550a0e46bdf7c86de34fc01d851c7d459121b263f7e6006569b5c56c1b99729
3
+ size 6825
runs/Apr10_18-34-17_a-System-Product-Name/events.out.tfevents.1744277658.a-System-Product-Name.3732.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:077269088fdeff49598501576226b19ba5213d865c52de75af6264cae8caa366
3
+ size 6825
runs/Apr10_18-37-43_a-System-Product-Name/events.out.tfevents.1744277865.a-System-Product-Name.3790.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da9df55b09bc9fc68636d8f436968692517803fd232949b3bd0041747faccf77
3
+ size 6824
runs/Apr10_18-42-36_a-System-Product-Name/events.out.tfevents.1744278158.a-System-Product-Name.3765.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e71461f72430fb3d8bdc40744aec81cf3b2d6f630827d10f21886a46bdcd916
3
+ size 80614
runs/Apr11_09-37-30_a-System-Product-Name/events.out.tfevents.1744331868.a-System-Product-Name.5092.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e162907e1e4112a532be28435ab50764255daa2b12f2341c73cecb26d6f33ce
3
+ size 34704
runs/Apr11_16-35-19_a-System-Product-Name/events.out.tfevents.1744356920.a-System-Product-Name.3984.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8452b054b6ab7a554e872e9ae9de97ea2086f15c1ef02323a2f61f9b0e068394
3
+ size 6824
runs/Apr11_16-40-58_a-System-Product-Name/events.out.tfevents.1744357261.a-System-Product-Name.3968.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fd170a9bb35071c29734776d5862c873a03dc21a188c4b2d930936e5074eae7
3
+ size 53068
runs/Apr13_10-24-01_a-System-Product-Name/events.out.tfevents.1744507443.a-System-Product-Name.4115.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b334a5b82be8367b70f00ce84d1b932af07171b723813cbbb8a3c332aa5bd2de
3
+ size 43886
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc3eb37efc28c6bd0868c9e651c0b91247fdec1b76daeab71458656dccd669c9
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:036e13859874852646f226ecb051e998e847dade0297fd78368df460c8423da3
3
  size 5496