End of training
Browse files
README.md
ADDED
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: jadasdn/wav2vec2-3
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- wer
|
8 |
+
model-index:
|
9 |
+
- name: wav2vec2-4
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# wav2vec2-4
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [jadasdn/wav2vec2-3](https://huggingface.co/jadasdn/wav2vec2-3) on the None dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.8336
|
21 |
+
- Wer: 0.3531
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 0.0001
|
41 |
+
- train_batch_size: 8
|
42 |
+
- eval_batch_size: 8
|
43 |
+
- seed: 42
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- lr_scheduler_warmup_steps: 1000
|
47 |
+
- num_epochs: 30
|
48 |
+
- mixed_precision_training: Native AMP
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
53 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
54 |
+
| 0.6872 | 0.5 | 500 | 0.3945 | 0.3562 |
|
55 |
+
| 0.5186 | 1.0 | 1000 | 0.4087 | 0.3701 |
|
56 |
+
| 0.5756 | 1.5 | 1500 | 0.4499 | 0.3770 |
|
57 |
+
| 0.4795 | 2.0 | 2000 | 0.4292 | 0.3754 |
|
58 |
+
| 0.379 | 2.5 | 2500 | 0.4430 | 0.3695 |
|
59 |
+
| 0.4879 | 3.0 | 3000 | 0.4530 | 0.3749 |
|
60 |
+
| 0.4527 | 3.5 | 3500 | 0.5052 | 0.3762 |
|
61 |
+
| 0.3305 | 4.0 | 4000 | 0.4820 | 0.3693 |
|
62 |
+
| 0.2707 | 4.5 | 4500 | 0.5045 | 0.3808 |
|
63 |
+
| 0.4131 | 5.0 | 5000 | 0.4771 | 0.3700 |
|
64 |
+
| 0.3045 | 5.5 | 5500 | 0.5130 | 0.3786 |
|
65 |
+
| 0.2459 | 6.0 | 6000 | 0.5071 | 0.3687 |
|
66 |
+
| 0.2674 | 6.5 | 6500 | 0.5515 | 0.3741 |
|
67 |
+
| 0.2224 | 7.0 | 7000 | 0.5358 | 0.3740 |
|
68 |
+
| 0.2228 | 7.5 | 7500 | 0.5648 | 0.3747 |
|
69 |
+
| 0.1992 | 8.0 | 8000 | 0.5644 | 0.3704 |
|
70 |
+
| 0.2089 | 8.5 | 8500 | 0.6098 | 0.3729 |
|
71 |
+
| 0.1795 | 9.0 | 9000 | 0.5837 | 0.3707 |
|
72 |
+
| 0.1584 | 9.5 | 9500 | 0.6143 | 0.3705 |
|
73 |
+
| 0.1741 | 10.0 | 10000 | 0.6294 | 0.3774 |
|
74 |
+
| 0.1461 | 10.5 | 10500 | 0.6406 | 0.3731 |
|
75 |
+
| 0.1448 | 11.0 | 11000 | 0.6352 | 0.3733 |
|
76 |
+
| 0.1318 | 11.5 | 11500 | 0.6338 | 0.3699 |
|
77 |
+
| 0.1396 | 12.0 | 12000 | 0.6440 | 0.3692 |
|
78 |
+
| 0.1226 | 12.5 | 12500 | 0.7047 | 0.3757 |
|
79 |
+
| 0.1232 | 13.0 | 13000 | 0.6815 | 0.3675 |
|
80 |
+
| 0.1168 | 13.5 | 13500 | 0.6607 | 0.3679 |
|
81 |
+
| 0.1128 | 14.0 | 14000 | 0.6650 | 0.3678 |
|
82 |
+
| 0.1046 | 14.5 | 14500 | 0.6944 | 0.3727 |
|
83 |
+
| 0.104 | 15.0 | 15000 | 0.7186 | 0.3652 |
|
84 |
+
| 0.097 | 15.5 | 15500 | 0.7224 | 0.3664 |
|
85 |
+
| 0.1022 | 16.0 | 16000 | 0.6928 | 0.3664 |
|
86 |
+
| 0.0987 | 16.5 | 16500 | 0.7248 | 0.3684 |
|
87 |
+
| 0.0905 | 17.0 | 17000 | 0.7157 | 0.3648 |
|
88 |
+
| 0.0863 | 17.5 | 17500 | 0.7410 | 0.3635 |
|
89 |
+
| 0.0829 | 18.0 | 18000 | 0.7629 | 0.3643 |
|
90 |
+
| 0.0788 | 18.5 | 18500 | 0.7371 | 0.3632 |
|
91 |
+
| 0.0799 | 19.0 | 19000 | 0.7554 | 0.3652 |
|
92 |
+
| 0.0744 | 19.5 | 19500 | 0.7886 | 0.3638 |
|
93 |
+
| 0.076 | 20.0 | 20000 | 0.7376 | 0.3631 |
|
94 |
+
| 0.0701 | 20.5 | 20500 | 0.7723 | 0.3586 |
|
95 |
+
| 0.0709 | 21.0 | 21000 | 0.7964 | 0.3613 |
|
96 |
+
| 0.0665 | 21.5 | 21500 | 0.7782 | 0.3576 |
|
97 |
+
| 0.066 | 22.0 | 22000 | 0.7885 | 0.3589 |
|
98 |
+
| 0.0621 | 22.5 | 22500 | 0.7906 | 0.3593 |
|
99 |
+
| 0.0614 | 23.0 | 23000 | 0.7737 | 0.3575 |
|
100 |
+
| 0.0626 | 23.5 | 23500 | 0.7903 | 0.3610 |
|
101 |
+
| 0.0595 | 24.0 | 24000 | 0.7937 | 0.3582 |
|
102 |
+
| 0.0572 | 24.5 | 24500 | 0.8263 | 0.3573 |
|
103 |
+
| 0.0553 | 25.0 | 25000 | 0.8125 | 0.3549 |
|
104 |
+
| 0.0529 | 25.5 | 25500 | 0.8154 | 0.3534 |
|
105 |
+
| 0.0524 | 26.0 | 26000 | 0.8018 | 0.3526 |
|
106 |
+
| 0.0513 | 26.5 | 26500 | 0.8160 | 0.3531 |
|
107 |
+
| 0.0491 | 27.0 | 27000 | 0.8117 | 0.3524 |
|
108 |
+
| 0.0456 | 27.5 | 27500 | 0.8263 | 0.3527 |
|
109 |
+
| 0.0479 | 28.0 | 28000 | 0.8368 | 0.3529 |
|
110 |
+
| 0.0459 | 28.5 | 28500 | 0.8325 | 0.3534 |
|
111 |
+
| 0.0427 | 29.0 | 29000 | 0.8331 | 0.3534 |
|
112 |
+
| 0.0458 | 29.5 | 29500 | 0.8315 | 0.3527 |
|
113 |
+
| 0.0436 | 30.0 | 30000 | 0.8336 | 0.3531 |
|
114 |
+
|
115 |
+
|
116 |
+
### Framework versions
|
117 |
+
|
118 |
+
- Transformers 4.35.2
|
119 |
+
- Pytorch 2.1.0+cu118
|
120 |
+
- Datasets 2.15.0
|
121 |
+
- Tokenizers 0.15.0
|