hippopotam
commited on
Commit
•
e9165d4
1
Parent(s):
18edff4
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- common_voice
|
7 |
+
metrics:
|
8 |
+
- wer
|
9 |
+
model-index:
|
10 |
+
- name: wav2vec2-common_voice-tr-demo
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Automatic Speech Recognition
|
14 |
+
type: automatic-speech-recognition
|
15 |
+
dataset:
|
16 |
+
name: common_voice
|
17 |
+
type: common_voice
|
18 |
+
config: tr
|
19 |
+
split: test
|
20 |
+
args: tr
|
21 |
+
metrics:
|
22 |
+
- name: Wer
|
23 |
+
type: wer
|
24 |
+
value: 0.49443366356858337
|
25 |
+
---
|
26 |
+
|
27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
28 |
+
should probably proofread and complete it, then remove this comment. -->
|
29 |
+
|
30 |
+
# wav2vec2-common_voice-tr-demo
|
31 |
+
|
32 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the common_voice dataset.
|
33 |
+
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 0.5314
|
35 |
+
- Wer: 0.4944
|
36 |
+
|
37 |
+
## Model description
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Intended uses & limitations
|
42 |
+
|
43 |
+
More information needed
|
44 |
+
|
45 |
+
## Training and evaluation data
|
46 |
+
|
47 |
+
More information needed
|
48 |
+
|
49 |
+
## Training procedure
|
50 |
+
|
51 |
+
### Training hyperparameters
|
52 |
+
|
53 |
+
The following hyperparameters were used during training:
|
54 |
+
- learning_rate: 0.0002
|
55 |
+
- train_batch_size: 32
|
56 |
+
- eval_batch_size: 16
|
57 |
+
- seed: 42
|
58 |
+
- gradient_accumulation_steps: 2
|
59 |
+
- total_train_batch_size: 64
|
60 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
61 |
+
- lr_scheduler_type: linear
|
62 |
+
- lr_scheduler_warmup_steps: 500
|
63 |
+
- num_epochs: 20.0
|
64 |
+
- mixed_precision_training: Native AMP
|
65 |
+
|
66 |
+
### Training results
|
67 |
+
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
69 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
70 |
+
| No log | 1.83 | 100 | 4.1084 | 1.0 |
|
71 |
+
| No log | 3.67 | 200 | 3.1519 | 1.0 |
|
72 |
+
| No log | 5.5 | 300 | 1.9348 | 0.9799 |
|
73 |
+
| No log | 7.34 | 400 | 0.7185 | 0.7490 |
|
74 |
+
| 3.6165 | 9.17 | 500 | 0.6041 | 0.6368 |
|
75 |
+
| 3.6165 | 11.01 | 600 | 0.5610 | 0.5771 |
|
76 |
+
| 3.6165 | 12.84 | 700 | 0.5292 | 0.5398 |
|
77 |
+
| 3.6165 | 14.68 | 800 | 0.5242 | 0.5083 |
|
78 |
+
| 3.6165 | 16.51 | 900 | 0.5443 | 0.5037 |
|
79 |
+
| 0.1894 | 18.35 | 1000 | 0.5314 | 0.4944 |
|
80 |
+
|
81 |
+
|
82 |
+
### Framework versions
|
83 |
+
|
84 |
+
- Transformers 4.29.2
|
85 |
+
- Pytorch 2.0.1
|
86 |
+
- Datasets 2.13.1
|
87 |
+
- Tokenizers 0.13.2
|