Commit
•
d6be281
1
Parent(s):
2a6c7a8
Model save
Browse files- README.md +77 -0
- model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/wav2vec2-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- wer
|
8 |
+
model-index:
|
9 |
+
- name: w2v2-base-pretrained_lr5e-5_at0.3_da1
|
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 |
+
# w2v2-base-pretrained_lr5e-5_at0.3_da1
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.2363
|
21 |
+
- Wer: 0.1773
|
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: 5e-05
|
41 |
+
- train_batch_size: 32
|
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: 500
|
47 |
+
- training_steps: 4000
|
48 |
+
- mixed_precision_training: Native AMP
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
53 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
54 |
+
| 15.0228 | 3.97 | 250 | 4.0018 | 1.0 |
|
55 |
+
| 3.1757 | 7.94 | 500 | 3.2733 | 1.0 |
|
56 |
+
| 3.0888 | 11.9 | 750 | 3.0842 | 1.0 |
|
57 |
+
| 1.8583 | 15.87 | 1000 | 0.8173 | 0.6087 |
|
58 |
+
| 0.3832 | 19.84 | 1250 | 0.6533 | 0.3520 |
|
59 |
+
| 0.2105 | 23.81 | 1500 | 0.7165 | 0.2448 |
|
60 |
+
| 0.1301 | 27.78 | 1750 | 0.9040 | 0.2016 |
|
61 |
+
| 0.0917 | 31.75 | 2000 | 1.0631 | 0.1961 |
|
62 |
+
| 0.0674 | 35.71 | 2250 | 1.0216 | 0.1905 |
|
63 |
+
| 0.0571 | 39.68 | 2500 | 1.1088 | 0.1854 |
|
64 |
+
| 0.0456 | 43.65 | 2750 | 1.2525 | 0.1747 |
|
65 |
+
| 0.0387 | 47.62 | 3000 | 1.1236 | 0.1845 |
|
66 |
+
| 0.034 | 51.59 | 3250 | 1.1696 | 0.1730 |
|
67 |
+
| 0.0291 | 55.56 | 3500 | 1.2542 | 0.1756 |
|
68 |
+
| 0.0284 | 59.52 | 3750 | 1.2190 | 0.1760 |
|
69 |
+
| 0.026 | 63.49 | 4000 | 1.2363 | 0.1773 |
|
70 |
+
|
71 |
+
|
72 |
+
### Framework versions
|
73 |
+
|
74 |
+
- Transformers 4.35.0
|
75 |
+
- Pytorch 2.0.0
|
76 |
+
- Datasets 2.14.6
|
77 |
+
- Tokenizers 0.14.1
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377629528
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9d6ad34b5854ae75d4af9eaf1e6a034c613cf0ef017d1112cdc8075153139bd
|
3 |
size 377629528
|