saribalgar
commited on
Commit
•
205d69a
1
Parent(s):
a3682a4
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,114 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- wer
|
7 |
+
model-index:
|
8 |
+
- name: wav2vec2-base-ms-with-lm
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# wav2vec2-base-ms-with-lm
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 1.1256
|
20 |
+
- Wer: 0.3991
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 0.0001
|
40 |
+
- train_batch_size: 4
|
41 |
+
- eval_batch_size: 8
|
42 |
+
- seed: 42
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: linear
|
45 |
+
- lr_scheduler_warmup_steps: 1000
|
46 |
+
- num_epochs: 100
|
47 |
+
- mixed_precision_training: Native AMP
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
52 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
53 |
+
| 4.0672 | 1.85 | 500 | 2.9666 | 1.0 |
|
54 |
+
| 1.6566 | 3.7 | 1000 | 0.7862 | 0.6177 |
|
55 |
+
| 0.6424 | 5.56 | 1500 | 0.6600 | 0.5478 |
|
56 |
+
| 0.4438 | 7.41 | 2000 | 0.6148 | 0.4835 |
|
57 |
+
| 0.3133 | 9.26 | 2500 | 0.6949 | 0.4516 |
|
58 |
+
| 0.2822 | 11.11 | 3000 | 0.6844 | 0.4533 |
|
59 |
+
| 0.2338 | 12.96 | 3500 | 0.7682 | 0.4634 |
|
60 |
+
| 0.2246 | 14.81 | 4000 | 0.8370 | 0.4925 |
|
61 |
+
| 0.1957 | 16.67 | 4500 | 0.8554 | 0.4377 |
|
62 |
+
| 0.1809 | 18.52 | 5000 | 0.7211 | 0.4505 |
|
63 |
+
| 0.1496 | 20.37 | 5500 | 0.8081 | 0.4354 |
|
64 |
+
| 0.1369 | 22.22 | 6000 | 0.9099 | 0.4360 |
|
65 |
+
| 0.1285 | 24.07 | 6500 | 0.8051 | 0.4231 |
|
66 |
+
| 0.1174 | 25.93 | 7000 | 0.9041 | 0.4505 |
|
67 |
+
| 0.1074 | 27.78 | 7500 | 0.8096 | 0.4310 |
|
68 |
+
| 0.0904 | 29.63 | 8000 | 0.8589 | 0.4237 |
|
69 |
+
| 0.0975 | 31.48 | 8500 | 0.9019 | 0.4142 |
|
70 |
+
| 0.0806 | 33.33 | 9000 | 0.8966 | 0.4382 |
|
71 |
+
| 0.0772 | 35.19 | 9500 | 1.0612 | 0.4181 |
|
72 |
+
| 0.0738 | 37.04 | 10000 | 0.8979 | 0.4215 |
|
73 |
+
| 0.0678 | 38.89 | 10500 | 0.9342 | 0.4103 |
|
74 |
+
| 0.0626 | 40.74 | 11000 | 0.9992 | 0.4187 |
|
75 |
+
| 0.0641 | 42.59 | 11500 | 1.0101 | 0.4120 |
|
76 |
+
| 0.0565 | 44.44 | 12000 | 0.9841 | 0.4287 |
|
77 |
+
| 0.0535 | 46.3 | 12500 | 1.0049 | 0.4097 |
|
78 |
+
| 0.0512 | 48.15 | 13000 | 0.9569 | 0.4080 |
|
79 |
+
| 0.0466 | 50.0 | 13500 | 0.9863 | 0.4276 |
|
80 |
+
| 0.0514 | 51.85 | 14000 | 0.9594 | 0.4120 |
|
81 |
+
| 0.0397 | 53.7 | 14500 | 0.9775 | 0.4103 |
|
82 |
+
| 0.0394 | 55.56 | 15000 | 1.0077 | 0.4131 |
|
83 |
+
| 0.0393 | 57.41 | 15500 | 0.9763 | 0.4108 |
|
84 |
+
| 0.0355 | 59.26 | 16000 | 1.1432 | 0.4226 |
|
85 |
+
| 0.0323 | 61.11 | 16500 | 1.1553 | 0.4192 |
|
86 |
+
| 0.0344 | 62.96 | 17000 | 1.0437 | 0.4203 |
|
87 |
+
| 0.0296 | 64.81 | 17500 | 1.0227 | 0.4209 |
|
88 |
+
| 0.0267 | 66.67 | 18000 | 1.0408 | 0.4287 |
|
89 |
+
| 0.0283 | 68.52 | 18500 | 1.0811 | 0.4192 |
|
90 |
+
| 0.0243 | 70.37 | 19000 | 1.0697 | 0.4075 |
|
91 |
+
| 0.0238 | 72.22 | 19500 | 1.1047 | 0.4164 |
|
92 |
+
| 0.0234 | 74.07 | 20000 | 1.1585 | 0.4142 |
|
93 |
+
| 0.02 | 75.93 | 20500 | 1.1183 | 0.4187 |
|
94 |
+
| 0.0231 | 77.78 | 21000 | 1.0923 | 0.4080 |
|
95 |
+
| 0.018 | 79.63 | 21500 | 1.1299 | 0.4058 |
|
96 |
+
| 0.0179 | 81.48 | 22000 | 1.0963 | 0.4008 |
|
97 |
+
| 0.0152 | 83.33 | 22500 | 1.0676 | 0.4002 |
|
98 |
+
| 0.0142 | 85.19 | 23000 | 1.1026 | 0.4047 |
|
99 |
+
| 0.0159 | 87.04 | 23500 | 1.0876 | 0.4058 |
|
100 |
+
| 0.0144 | 88.89 | 24000 | 1.0943 | 0.3963 |
|
101 |
+
| 0.0152 | 90.74 | 24500 | 1.0827 | 0.4075 |
|
102 |
+
| 0.0155 | 92.59 | 25000 | 1.0982 | 0.4019 |
|
103 |
+
| 0.0124 | 94.44 | 25500 | 1.1284 | 0.3985 |
|
104 |
+
| 0.0132 | 96.3 | 26000 | 1.1233 | 0.3991 |
|
105 |
+
| 0.0109 | 98.15 | 26500 | 1.1196 | 0.3980 |
|
106 |
+
| 0.0102 | 100.0 | 27000 | 1.1256 | 0.3991 |
|
107 |
+
|
108 |
+
|
109 |
+
### Framework versions
|
110 |
+
|
111 |
+
- Transformers 4.24.0
|
112 |
+
- Pytorch 2.0.0+cu118
|
113 |
+
- Datasets 1.18.3
|
114 |
+
- Tokenizers 0.13.3
|