zainulhakim
commited on
Commit
•
df7f9c6
1
Parent(s):
07f6588
End of training
Browse files
README.md
CHANGED
@@ -1,24 +1,24 @@
|
|
1 |
---
|
2 |
-
base_model: zainulhakim/240615-wav2vec2-ASR-English
|
3 |
license: apache-2.0
|
4 |
-
|
5 |
-
- wer
|
6 |
tags:
|
7 |
- generated_from_trainer
|
|
|
|
|
8 |
model-index:
|
9 |
-
- name:
|
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 |
-
#
|
17 |
|
18 |
-
This model is a fine-tuned version of [
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss:
|
21 |
-
- Wer: 0.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -38,7 +38,7 @@ More information needed
|
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
- learning_rate: 0.0001
|
41 |
-
- train_batch_size:
|
42 |
- eval_batch_size: 8
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
@@ -51,12 +51,10 @@ The following hyperparameters were used during training:
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
54 |
-
| No log |
|
55 |
-
| No log |
|
56 |
-
| No log |
|
57 |
-
| No log |
|
58 |
-
| 1.766 | 25.0 | 500 | 1.0466 | 0.5714 |
|
59 |
-
| 1.766 | 30.0 | 600 | 0.8851 | 0.5584 |
|
60 |
|
61 |
|
62 |
### Framework versions
|
|
|
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: 240615-wav2vec2-ASR-Chinese
|
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 |
+
# 240615-wav2vec2-ASR-Chinese
|
17 |
|
18 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.2831
|
21 |
+
- Wer: 0.2399
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
- learning_rate: 0.0001
|
41 |
+
- train_batch_size: 5
|
42 |
- eval_batch_size: 8
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
54 |
+
| No log | 6.25 | 100 | 1.2831 | 0.2399 |
|
55 |
+
| No log | 12.5 | 200 | 1.2996 | 0.2657 |
|
56 |
+
| No log | 18.75 | 300 | 1.3705 | 0.3092 |
|
57 |
+
| No log | 25.0 | 400 | 1.3119 | 0.3269 |
|
|
|
|
|
58 |
|
59 |
|
60 |
### Framework versions
|