henil panchal
commited on
Commit
•
c8e58de
1
Parent(s):
0e517d1
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- wer
|
7 |
+
model-index:
|
8 |
+
- name: wav2vec2-large-xls-r-300m-telugu-asr
|
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-large-xls-r-300m-telugu-asr
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 3.8208
|
20 |
+
- Wer: 1.0395
|
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: 0.0003
|
40 |
+
- train_batch_size: 8
|
41 |
+
- eval_batch_size: 8
|
42 |
+
- seed: 42
|
43 |
+
- gradient_accumulation_steps: 2
|
44 |
+
- total_train_batch_size: 16
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- lr_scheduler_warmup_steps: 500
|
48 |
+
- num_epochs: 30
|
49 |
+
- mixed_precision_training: Native AMP
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
55 |
+
| 11.4834 | 1.37 | 200 | 4.8950 | 1.0 |
|
56 |
+
| 3.9043 | 2.74 | 400 | 3.8879 | 1.0 |
|
57 |
+
| 3.7152 | 4.11 | 600 | 3.6273 | 1.0 |
|
58 |
+
| 3.6229 | 5.48 | 800 | 3.8105 | 1.0 |
|
59 |
+
| 3.5465 | 6.85 | 1000 | 3.6970 | 1.0 |
|
60 |
+
| 3.5106 | 8.22 | 1200 | 3.6657 | 1.0 |
|
61 |
+
| 3.3731 | 9.59 | 1400 | 3.4669 | 0.9995 |
|
62 |
+
| 3.183 | 10.96 | 1600 | 3.1894 | 0.9983 |
|
63 |
+
| 2.9215 | 12.33 | 1800 | 2.9099 | 0.9993 |
|
64 |
+
| 2.5357 | 13.7 | 2000 | 2.8166 | 1.0407 |
|
65 |
+
| 2.1257 | 15.07 | 2200 | 2.6122 | 1.0205 |
|
66 |
+
| 1.7549 | 16.44 | 2400 | 2.5981 | 1.0457 |
|
67 |
+
| 1.4642 | 17.81 | 2600 | 2.5619 | 1.0015 |
|
68 |
+
| 1.1814 | 19.18 | 2800 | 2.8769 | 0.9836 |
|
69 |
+
| 0.9759 | 20.55 | 3000 | 2.8497 | 1.0078 |
|
70 |
+
| 0.8066 | 21.92 | 3200 | 3.1365 | 1.0655 |
|
71 |
+
| 0.6614 | 23.29 | 3400 | 3.1759 | 0.9964 |
|
72 |
+
| 0.5687 | 24.66 | 3600 | 3.3751 | 1.0103 |
|
73 |
+
| 0.4987 | 26.03 | 3800 | 3.5111 | 1.0180 |
|
74 |
+
| 0.4304 | 27.4 | 4000 | 3.6908 | 1.0200 |
|
75 |
+
| 0.3818 | 28.77 | 4200 | 3.8208 | 1.0395 |
|
76 |
+
|
77 |
+
|
78 |
+
### Framework versions
|
79 |
+
|
80 |
+
- Transformers 4.24.0
|
81 |
+
- Pytorch 1.10.0+cu113
|
82 |
+
- Datasets 1.18.3
|
83 |
+
- Tokenizers 0.13.2
|