update model card README.md
Browse files
README.md
CHANGED
@@ -1,7 +1,5 @@
|
|
1 |
---
|
2 |
tags:
|
3 |
-
- automatic-speech-recognition
|
4 |
-
- gary109/AI_Light_Dance
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
- ai_light_dance
|
@@ -9,7 +7,20 @@ metrics:
|
|
9 |
- wer
|
10 |
model-index:
|
11 |
- name: ai-light-dance_drums_ft_pretrain_wav2vec2-base-new-v6-1
|
12 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
---
|
14 |
|
15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -17,10 +28,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
# ai-light-dance_drums_ft_pretrain_wav2vec2-base-new-v6-1
|
19 |
|
20 |
-
This model is a fine-tuned version of [gary109/ai-light-
|
21 |
It achieves the following results on the evaluation set:
|
22 |
-
- Loss: 0.
|
23 |
-
- Wer: 0.
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -39,122 +50,122 @@ More information needed
|
|
39 |
### Training hyperparameters
|
40 |
|
41 |
The following hyperparameters were used during training:
|
42 |
-
- learning_rate: 0.
|
43 |
-
- train_batch_size:
|
44 |
-
- eval_batch_size:
|
45 |
- seed: 42
|
46 |
-
- gradient_accumulation_steps:
|
47 |
-
- total_train_batch_size:
|
48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
- lr_scheduler_type: linear
|
50 |
-
- lr_scheduler_warmup_steps:
|
51 |
- num_epochs: 100.0
|
52 |
- mixed_precision_training: Native AMP
|
53 |
|
54 |
### Training results
|
55 |
|
56 |
-
| Training Loss | Epoch | Step
|
57 |
-
|
58 |
-
|
|
59 |
-
|
|
60 |
-
|
|
61 |
-
|
|
62 |
-
|
|
63 |
-
|
|
64 |
-
|
|
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 |
-
| 0.
|
106 |
-
| 0.
|
107 |
-
| 0.
|
108 |
-
| 0.
|
109 |
-
| 0.
|
110 |
-
| 0.
|
111 |
-
| 0.
|
112 |
-
| 0.
|
113 |
-
| 0.
|
114 |
-
| 0.
|
115 |
-
| 0.
|
116 |
-
| 0.
|
117 |
-
| 0.
|
118 |
-
| 0.
|
119 |
-
| 0.
|
120 |
-
| 0.
|
121 |
-
| 0.
|
122 |
-
| 0.
|
123 |
-
| 0.
|
124 |
-
| 0.
|
125 |
-
| 0.
|
126 |
-
| 0.
|
127 |
-
| 0.
|
128 |
-
| 0.
|
129 |
-
| 0.
|
130 |
-
| 0.
|
131 |
-
| 0.
|
132 |
-
| 0.
|
133 |
-
| 0.
|
134 |
-
| 0.
|
135 |
-
| 0.
|
136 |
-
| 0.
|
137 |
-
| 0.
|
138 |
-
|
|
139 |
-
| 0.
|
140 |
-
| 0.
|
141 |
-
| 0.
|
142 |
-
| 0.
|
143 |
-
| 0.
|
144 |
-
| 0.
|
145 |
-
| 0.
|
146 |
-
| 0.
|
147 |
-
| 0.
|
148 |
-
| 0.
|
149 |
-
| 0.
|
150 |
-
| 0.
|
151 |
-
| 0.
|
152 |
-
| 0.
|
153 |
-
| 0.
|
154 |
-
| 0.
|
155 |
-
| 0.
|
156 |
-
| 0.
|
157 |
-
| 0.
|
158 |
|
159 |
|
160 |
### Framework versions
|
|
|
1 |
---
|
2 |
tags:
|
|
|
|
|
3 |
- generated_from_trainer
|
4 |
datasets:
|
5 |
- ai_light_dance
|
|
|
7 |
- wer
|
8 |
model-index:
|
9 |
- name: ai-light-dance_drums_ft_pretrain_wav2vec2-base-new-v6-1
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
name: Automatic Speech Recognition
|
13 |
+
type: automatic-speech-recognition
|
14 |
+
dataset:
|
15 |
+
name: ai_light_dance
|
16 |
+
type: ai_light_dance
|
17 |
+
config: onset-idmt-mdb-enst2
|
18 |
+
split: train
|
19 |
+
args: onset-idmt-mdb-enst2
|
20 |
+
metrics:
|
21 |
+
- name: Wer
|
22 |
+
type: wer
|
23 |
+
value: 0.32686630113876003
|
24 |
---
|
25 |
|
26 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
28 |
|
29 |
# ai-light-dance_drums_ft_pretrain_wav2vec2-base-new-v6-1
|
30 |
|
31 |
+
This model is a fine-tuned version of [gary109/ai-light-dance_drums_ft_pretrain_wav2vec2-base-new-v6-1](https://huggingface.co/gary109/ai-light-dance_drums_ft_pretrain_wav2vec2-base-new-v6-1) on the ai_light_dance dataset.
|
32 |
It achieves the following results on the evaluation set:
|
33 |
+
- Loss: 0.6187
|
34 |
+
- Wer: 0.3269
|
35 |
|
36 |
## Model description
|
37 |
|
|
|
50 |
### Training hyperparameters
|
51 |
|
52 |
The following hyperparameters were used during training:
|
53 |
+
- learning_rate: 0.0001
|
54 |
+
- train_batch_size: 2
|
55 |
+
- eval_batch_size: 2
|
56 |
- seed: 42
|
57 |
+
- gradient_accumulation_steps: 2
|
58 |
+
- total_train_batch_size: 4
|
59 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
- lr_scheduler_type: linear
|
61 |
+
- lr_scheduler_warmup_steps: 10
|
62 |
- num_epochs: 100.0
|
63 |
- mixed_precision_training: Native AMP
|
64 |
|
65 |
### Training results
|
66 |
|
67 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
68 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
69 |
+
| 0.2764 | 1.0 | 141 | 0.7125 | 0.3619 |
|
70 |
+
| 0.5415 | 2.0 | 282 | 0.7252 | 0.3682 |
|
71 |
+
| 0.3324 | 3.0 | 423 | 0.6779 | 0.3728 |
|
72 |
+
| 0.4244 | 4.0 | 564 | 0.7403 | 0.3737 |
|
73 |
+
| 0.5234 | 5.0 | 705 | 0.8086 | 0.3534 |
|
74 |
+
| 0.3339 | 6.0 | 846 | 0.7187 | 0.3619 |
|
75 |
+
| 0.5016 | 7.0 | 987 | 0.8582 | 0.3602 |
|
76 |
+
| 0.3376 | 8.0 | 1128 | 0.8801 | 0.3674 |
|
77 |
+
| 0.3507 | 9.0 | 1269 | 0.8524 | 0.3560 |
|
78 |
+
| 0.4844 | 10.0 | 1410 | 0.7152 | 0.3648 |
|
79 |
+
| 0.4282 | 11.0 | 1551 | 0.6719 | 0.3475 |
|
80 |
+
| 0.4398 | 12.0 | 1692 | 0.7130 | 0.3686 |
|
81 |
+
| 0.331 | 13.0 | 1833 | 0.6425 | 0.3627 |
|
82 |
+
| 0.4488 | 14.0 | 1974 | 0.6483 | 0.3648 |
|
83 |
+
| 0.3876 | 15.0 | 2115 | 0.6375 | 0.3509 |
|
84 |
+
| 0.3361 | 16.0 | 2256 | 0.6791 | 0.3703 |
|
85 |
+
| 0.344 | 17.0 | 2397 | 0.7279 | 0.3551 |
|
86 |
+
| 0.3198 | 18.0 | 2538 | 0.6801 | 0.3509 |
|
87 |
+
| 0.2753 | 19.0 | 2679 | 0.6239 | 0.3509 |
|
88 |
+
| 0.2962 | 20.0 | 2820 | 0.7419 | 0.3442 |
|
89 |
+
| 0.7503 | 21.0 | 2961 | 0.7279 | 0.3501 |
|
90 |
+
| 0.4013 | 22.0 | 3102 | 0.6899 | 0.3792 |
|
91 |
+
| 0.5134 | 23.0 | 3243 | 0.6572 | 0.3787 |
|
92 |
+
| 0.3144 | 24.0 | 3384 | 0.5882 | 0.3543 |
|
93 |
+
| 0.3534 | 25.0 | 3525 | 0.5661 | 0.3416 |
|
94 |
+
| 0.2555 | 26.0 | 3666 | 0.5977 | 0.3589 |
|
95 |
+
| 0.3524 | 27.0 | 3807 | 0.5953 | 0.3585 |
|
96 |
+
| 0.314 | 28.0 | 3948 | 0.6359 | 0.3593 |
|
97 |
+
| 0.2565 | 29.0 | 4089 | 0.6192 | 0.3615 |
|
98 |
+
| 0.5023 | 30.0 | 4230 | 0.6229 | 0.3378 |
|
99 |
+
| 0.3025 | 31.0 | 4371 | 0.6002 | 0.3442 |
|
100 |
+
| 0.3329 | 32.0 | 4512 | 0.6235 | 0.3513 |
|
101 |
+
| 0.3744 | 33.0 | 4653 | 0.5782 | 0.3416 |
|
102 |
+
| 0.2899 | 34.0 | 4794 | 0.5835 | 0.3336 |
|
103 |
+
| 0.306 | 35.0 | 4935 | 0.6061 | 0.3496 |
|
104 |
+
| 0.2519 | 36.0 | 5076 | 0.5958 | 0.3652 |
|
105 |
+
| 0.3201 | 37.0 | 5217 | 0.5778 | 0.3652 |
|
106 |
+
| 0.3011 | 38.0 | 5358 | 0.6238 | 0.3589 |
|
107 |
+
| 0.2882 | 39.0 | 5499 | 0.6501 | 0.3361 |
|
108 |
+
| 0.2542 | 40.0 | 5640 | 0.6341 | 0.3488 |
|
109 |
+
| 0.2717 | 41.0 | 5781 | 0.5890 | 0.3530 |
|
110 |
+
| 0.3197 | 42.0 | 5922 | 0.5877 | 0.3471 |
|
111 |
+
| 0.2816 | 43.0 | 6063 | 0.6614 | 0.3420 |
|
112 |
+
| 0.3301 | 44.0 | 6204 | 0.6334 | 0.3475 |
|
113 |
+
| 0.2466 | 45.0 | 6345 | 0.6663 | 0.3429 |
|
114 |
+
| 0.2908 | 46.0 | 6486 | 0.5941 | 0.3475 |
|
115 |
+
| 0.2785 | 47.0 | 6627 | 0.6337 | 0.3568 |
|
116 |
+
| 0.2361 | 48.0 | 6768 | 0.5845 | 0.3399 |
|
117 |
+
| 0.4729 | 49.0 | 6909 | 0.6466 | 0.3425 |
|
118 |
+
| 0.5103 | 50.0 | 7050 | 0.7112 | 0.3416 |
|
119 |
+
| 0.2676 | 51.0 | 7191 | 0.6260 | 0.3307 |
|
120 |
+
| 0.3533 | 52.0 | 7332 | 0.7327 | 0.3454 |
|
121 |
+
| 0.3308 | 53.0 | 7473 | 0.7150 | 0.3277 |
|
122 |
+
| 0.2617 | 54.0 | 7614 | 0.6412 | 0.3391 |
|
123 |
+
| 0.2901 | 55.0 | 7755 | 0.6225 | 0.3391 |
|
124 |
+
| 0.2847 | 56.0 | 7896 | 0.7385 | 0.3391 |
|
125 |
+
| 0.2621 | 57.0 | 8037 | 0.7241 | 0.3496 |
|
126 |
+
| 0.2477 | 58.0 | 8178 | 0.6957 | 0.3429 |
|
127 |
+
| 0.3147 | 59.0 | 8319 | 0.6808 | 0.3425 |
|
128 |
+
| 0.3761 | 60.0 | 8460 | 0.6710 | 0.3450 |
|
129 |
+
| 0.2609 | 61.0 | 8601 | 0.6629 | 0.3345 |
|
130 |
+
| 0.388 | 62.0 | 8742 | 0.6688 | 0.3463 |
|
131 |
+
| 0.3684 | 63.0 | 8883 | 0.7018 | 0.3340 |
|
132 |
+
| 0.2494 | 64.0 | 9024 | 0.6611 | 0.3399 |
|
133 |
+
| 0.2641 | 65.0 | 9165 | 0.6828 | 0.3399 |
|
134 |
+
| 0.2716 | 66.0 | 9306 | 0.6409 | 0.3294 |
|
135 |
+
| 0.2595 | 67.0 | 9447 | 0.6056 | 0.3231 |
|
136 |
+
| 0.2683 | 68.0 | 9588 | 0.6203 | 0.3332 |
|
137 |
+
| 0.2571 | 69.0 | 9729 | 0.6484 | 0.3336 |
|
138 |
+
| 0.2593 | 70.0 | 9870 | 0.6597 | 0.3294 |
|
139 |
+
| 0.229 | 71.0 | 10011 | 0.6354 | 0.3235 |
|
140 |
+
| 0.281 | 72.0 | 10152 | 0.6398 | 0.3294 |
|
141 |
+
| 0.3779 | 73.0 | 10293 | 0.6871 | 0.3345 |
|
142 |
+
| 0.2998 | 74.0 | 10434 | 0.7329 | 0.3323 |
|
143 |
+
| 0.2095 | 75.0 | 10575 | 0.7365 | 0.3239 |
|
144 |
+
| 0.247 | 76.0 | 10716 | 0.6384 | 0.3290 |
|
145 |
+
| 0.2095 | 77.0 | 10857 | 0.6703 | 0.3345 |
|
146 |
+
| 0.2074 | 78.0 | 10998 | 0.6577 | 0.3425 |
|
147 |
+
| 0.2519 | 79.0 | 11139 | 0.6359 | 0.3370 |
|
148 |
+
| 0.2046 | 80.0 | 11280 | 0.6222 | 0.3256 |
|
149 |
+
| 1.3195 | 81.0 | 11421 | 0.6126 | 0.3345 |
|
150 |
+
| 0.2821 | 82.0 | 11562 | 0.6193 | 0.3294 |
|
151 |
+
| 0.3256 | 83.0 | 11703 | 0.6140 | 0.3336 |
|
152 |
+
| 0.2743 | 84.0 | 11844 | 0.6204 | 0.3290 |
|
153 |
+
| 0.2761 | 85.0 | 11985 | 0.6599 | 0.3252 |
|
154 |
+
| 0.224 | 86.0 | 12126 | 0.6580 | 0.3294 |
|
155 |
+
| 0.2106 | 87.0 | 12267 | 0.6298 | 0.3294 |
|
156 |
+
| 0.2706 | 88.0 | 12408 | 0.6411 | 0.3281 |
|
157 |
+
| 0.2523 | 89.0 | 12549 | 0.6243 | 0.3264 |
|
158 |
+
| 0.3635 | 90.0 | 12690 | 0.6297 | 0.3290 |
|
159 |
+
| 0.353 | 91.0 | 12831 | 0.6145 | 0.3235 |
|
160 |
+
| 0.2491 | 92.0 | 12972 | 0.6296 | 0.3197 |
|
161 |
+
| 0.1999 | 93.0 | 13113 | 0.6329 | 0.3222 |
|
162 |
+
| 0.2417 | 94.0 | 13254 | 0.6200 | 0.3222 |
|
163 |
+
| 0.2397 | 95.0 | 13395 | 0.6137 | 0.3269 |
|
164 |
+
| 0.2275 | 96.0 | 13536 | 0.6237 | 0.3277 |
|
165 |
+
| 0.207 | 97.0 | 13677 | 0.6230 | 0.3235 |
|
166 |
+
| 0.2704 | 98.0 | 13818 | 0.6239 | 0.3281 |
|
167 |
+
| 0.2119 | 99.0 | 13959 | 0.6224 | 0.3277 |
|
168 |
+
| 0.2561 | 100.0 | 14100 | 0.6187 | 0.3269 |
|
169 |
|
170 |
|
171 |
### Framework versions
|