Hugging Face's logo

rdg-rvc-dev
/
whisper-medium-pt-nonverbal-v3-1-demo

TensorBoard
Safetensors
whisper
Generated from Trainer
Model card Files Metrics Community
rdg-rvc-dev commited on
Commit
3558b0d
·
verified ·
1 Parent(s): 51a4bfc

Model save

Browse files
Files changed (3) hide show
  1. README.md +25 -10
  2. model.safetensors +1 -1
  3. runs/Jan18_17-58-13_DESKTOP-0Q1NC6M/events.out.tfevents.1737234036.DESKTOP-0Q1NC6M.20256.1 +2 -2
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.5210
21
- - Wer: 44.1379
22
 
23
  ## Model description
24
 
@@ -44,18 +44,33 @@ The following hyperparameters were used during training:
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 500
47
- - training_steps: 500
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss | Wer |
53
- |:-------------:|:-------:|:----:|:---------------:|:-------:|
54
- | 1.8256 | 2.7778 | 100 | 1.8063 | 47.5862 |
55
- | 0.0485 | 5.5556 | 200 | 0.3169 | 28.2759 |
56
- | 0.0217 | 8.3333 | 300 | 0.4161 | 29.6552 |
57
- | 0.0098 | 11.1111 | 400 | 0.5509 | 31.0345 |
58
- | 0.0324 | 13.8889 | 500 | 0.5210 | 44.1379 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
59
 
60
 
61
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.5803
21
+ - Wer: 47.7893
22
 
23
  ## Model description
24
 
 
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 500
47
+ - training_steps: 2000
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
53
+ |:-------------:|:------:|:----:|:---------------:|:--------:|
54
+ | 2.3675 | 0.2841 | 100 | 2.3957 | 136.7360 |
55
+ | 0.3724 | 0.5682 | 200 | 0.7022 | 141.4824 |
56
+ | 0.2198 | 0.8523 | 300 | 0.6064 | 113.4590 |
57
+ | 0.1343 | 1.1364 | 400 | 0.6187 | 68.3355 |
58
+ | 0.1647 | 1.4205 | 500 | 0.6852 | 88.4915 |
59
+ | 0.1516 | 1.7045 | 600 | 0.6420 | 230.7542 |
60
+ | 0.1679 | 1.9886 | 700 | 0.4757 | 58.0624 |
61
+ | 0.0954 | 2.2727 | 800 | 0.5675 | 48.1144 |
62
+ | 0.0653 | 2.5568 | 900 | 0.7046 | 66.2549 |
63
+ | 0.0906 | 2.8409 | 1000 | 0.4930 | 41.6775 |
64
+ | 0.0363 | 3.125 | 1100 | 0.5209 | 54.2913 |
65
+ | 0.0476 | 3.4091 | 1200 | 0.5836 | 49.6099 |
66
+ | 0.075 | 3.6932 | 1300 | 0.5253 | 49.1547 |
67
+ | 0.0274 | 3.9773 | 1400 | 0.5842 | 48.3095 |
68
+ | 0.0118 | 4.2614 | 1500 | 0.5568 | 45.0585 |
69
+ | 0.0121 | 4.5455 | 1600 | 0.5740 | 48.6996 |
70
+ | 0.0111 | 4.8295 | 1700 | 0.5486 | 48.8296 |
71
+ | 0.0055 | 5.1136 | 1800 | 0.5646 | 46.8791 |
72
+ | 0.0032 | 5.3977 | 1900 | 0.5771 | 47.9844 |
73
+ | 0.0043 | 5.6818 | 2000 | 0.5803 | 47.7893 |
74
 
75
 
76
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5761f8064f8c61604655dedb62d3c4be2576a1aff7f4fff5aaf444547d697bab
3
  size 3055544304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92b8670dfe12544ac78929262a968d560b73ca88d5dbe081dc61db1a79bde24c
3
  size 3055544304
runs/Jan18_17-58-13_DESKTOP-0Q1NC6M/events.out.tfevents.1737234036.DESKTOP-0Q1NC6M.20256.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7419c5b3f6c92a6b2aaccd0b2738f1b04d430cc15701ca2dc4c820862b3f3b66
3
- size 29049
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7119cd352b93cf48641740816440a0d9ff03e3092139306dbfb8dcb4fec0afd
3
+ size 29403