update model card README.md
Browse files
README.md
CHANGED
@@ -1,8 +1,6 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
tags:
|
4 |
-
- automatic-speech-recognition
|
5 |
-
- gary109/AI_Light_Dance
|
6 |
- generated_from_trainer
|
7 |
model-index:
|
8 |
- name: ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1
|
@@ -14,10 +12,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
# ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1
|
16 |
|
17 |
-
This model is a fine-tuned version of [gary109/ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1](https://huggingface.co/gary109/ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1) on the
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 0.
|
20 |
-
- Wer: 0.
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -36,72 +34,70 @@ More information needed
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
-
- learning_rate:
|
40 |
-
- train_batch_size:
|
41 |
-
- eval_batch_size:
|
42 |
- seed: 42
|
43 |
-
- gradient_accumulation_steps: 8
|
44 |
-
- total_train_batch_size: 64
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
-
- lr_scheduler_warmup_steps:
|
48 |
- num_epochs: 50.0
|
49 |
- mixed_precision_training: Native AMP
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
-
| Training Loss | Epoch | Step
|
54 |
-
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.
|
79 |
-
| 0.
|
80 |
-
| 0.
|
81 |
-
| 0.
|
82 |
-
| 0.
|
83 |
-
| 0.
|
84 |
-
| 0.
|
85 |
-
| 0.
|
86 |
-
| 0.
|
87 |
-
| 0.
|
88 |
-
| 0.
|
89 |
-
| 0.
|
90 |
-
| 0.
|
91 |
-
| 0.
|
92 |
-
| 0.
|
93 |
-
| 0.
|
94 |
-
| 0.
|
95 |
-
| 0.
|
96 |
-
| 0.
|
97 |
-
| 0.
|
98 |
-
| 0.
|
99 |
-
| 0.
|
100 |
-
| 0.
|
101 |
-
| 0.
|
102 |
-
| 0.
|
103 |
-
| 0.
|
104 |
-
| 0.
|
105 |
|
106 |
|
107 |
### Framework versions
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
tags:
|
|
|
|
|
4 |
- generated_from_trainer
|
5 |
model-index:
|
6 |
- name: ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1
|
|
|
12 |
|
13 |
# ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1
|
14 |
|
15 |
+
This model is a fine-tuned version of [gary109/ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1](https://huggingface.co/gary109/ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1) on the None dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 0.5709
|
18 |
+
- Wer: 0.2379
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
34 |
### Training hyperparameters
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 1e-06
|
38 |
+
- train_batch_size: 2
|
39 |
+
- eval_batch_size: 2
|
40 |
- seed: 42
|
|
|
|
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
+
- lr_scheduler_warmup_steps: 1000
|
44 |
- num_epochs: 50.0
|
45 |
- mixed_precision_training: Native AMP
|
46 |
|
47 |
### Training results
|
48 |
|
49 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
50 |
+
|:-------------:|:-----:|:------:|:---------------:|:------:|
|
51 |
+
| 0.3909 | 1.0 | 2309 | 0.5615 | 0.2459 |
|
52 |
+
| 0.4094 | 2.0 | 4618 | 0.5654 | 0.2439 |
|
53 |
+
| 0.326 | 3.0 | 6927 | 0.5568 | 0.2470 |
|
54 |
+
| 0.4577 | 4.0 | 9236 | 0.5795 | 0.2474 |
|
55 |
+
| 0.3628 | 5.0 | 11545 | 0.5459 | 0.2463 |
|
56 |
+
| 0.3135 | 6.0 | 13854 | 0.5582 | 0.2473 |
|
57 |
+
| 0.5058 | 7.0 | 16163 | 0.5677 | 0.2439 |
|
58 |
+
| 0.3188 | 8.0 | 18472 | 0.5646 | 0.2445 |
|
59 |
+
| 0.3589 | 9.0 | 20781 | 0.5626 | 0.2479 |
|
60 |
+
| 0.4021 | 10.0 | 23090 | 0.5722 | 0.2452 |
|
61 |
+
| 0.4362 | 11.0 | 25399 | 0.5659 | 0.2431 |
|
62 |
+
| 0.3215 | 12.0 | 27708 | 0.5658 | 0.2445 |
|
63 |
+
| 0.3646 | 13.0 | 30017 | 0.5785 | 0.2459 |
|
64 |
+
| 0.3757 | 14.0 | 32326 | 0.5757 | 0.2418 |
|
65 |
+
| 0.3311 | 15.0 | 34635 | 0.5672 | 0.2455 |
|
66 |
+
| 0.3709 | 16.0 | 36944 | 0.5669 | 0.2434 |
|
67 |
+
| 0.3342 | 17.0 | 39253 | 0.5610 | 0.2455 |
|
68 |
+
| 0.3236 | 18.0 | 41562 | 0.5652 | 0.2436 |
|
69 |
+
| 0.3566 | 19.0 | 43871 | 0.5773 | 0.2407 |
|
70 |
+
| 0.2912 | 20.0 | 46180 | 0.5764 | 0.2453 |
|
71 |
+
| 0.3652 | 21.0 | 48489 | 0.5732 | 0.2423 |
|
72 |
+
| 0.3785 | 22.0 | 50798 | 0.5696 | 0.2423 |
|
73 |
+
| 0.3968 | 23.0 | 53107 | 0.5690 | 0.2429 |
|
74 |
+
| 0.2968 | 24.0 | 55416 | 0.5800 | 0.2427 |
|
75 |
+
| 0.428 | 25.0 | 57725 | 0.5704 | 0.2441 |
|
76 |
+
| 0.383 | 26.0 | 60034 | 0.5739 | 0.2450 |
|
77 |
+
| 0.3694 | 27.0 | 62343 | 0.5791 | 0.2437 |
|
78 |
+
| 0.3449 | 28.0 | 64652 | 0.5780 | 0.2451 |
|
79 |
+
| 0.3008 | 29.0 | 66961 | 0.5749 | 0.2418 |
|
80 |
+
| 0.3939 | 30.0 | 69270 | 0.5737 | 0.2424 |
|
81 |
+
| 0.3451 | 31.0 | 71579 | 0.5805 | 0.2402 |
|
82 |
+
| 0.3513 | 32.0 | 73888 | 0.5670 | 0.2379 |
|
83 |
+
| 0.3866 | 33.0 | 76197 | 0.5706 | 0.2389 |
|
84 |
+
| 0.3831 | 34.0 | 78506 | 0.5635 | 0.2401 |
|
85 |
+
| 0.3641 | 35.0 | 80815 | 0.5708 | 0.2405 |
|
86 |
+
| 0.3345 | 36.0 | 83124 | 0.5699 | 0.2405 |
|
87 |
+
| 0.2902 | 37.0 | 85433 | 0.5711 | 0.2373 |
|
88 |
+
| 0.2868 | 38.0 | 87742 | 0.5713 | 0.2389 |
|
89 |
+
| 0.3232 | 39.0 | 90051 | 0.5702 | 0.2392 |
|
90 |
+
| 0.3277 | 40.0 | 92360 | 0.5658 | 0.2393 |
|
91 |
+
| 0.3234 | 41.0 | 94669 | 0.5732 | 0.2412 |
|
92 |
+
| 0.3625 | 42.0 | 96978 | 0.5740 | 0.2396 |
|
93 |
+
| 0.4075 | 43.0 | 99287 | 0.5733 | 0.2389 |
|
94 |
+
| 0.3473 | 44.0 | 101596 | 0.5735 | 0.2394 |
|
95 |
+
| 0.3157 | 45.0 | 103905 | 0.5721 | 0.2391 |
|
96 |
+
| 0.3866 | 46.0 | 106214 | 0.5715 | 0.2381 |
|
97 |
+
| 0.4062 | 47.0 | 108523 | 0.5711 | 0.2380 |
|
98 |
+
| 0.3871 | 48.0 | 110832 | 0.5716 | 0.2380 |
|
99 |
+
| 0.2924 | 49.0 | 113141 | 0.5723 | 0.2374 |
|
100 |
+
| 0.3655 | 50.0 | 115450 | 0.5709 | 0.2379 |
|
101 |
|
102 |
|
103 |
### Framework versions
|