xiaoming-leza
commited on
Commit
•
cff9c11
1
Parent(s):
37ce775
update model card README.md
Browse files
README.md
CHANGED
@@ -1,11 +1,7 @@
|
|
1 |
---
|
2 |
-
language:
|
3 |
-
- tr
|
4 |
license: apache-2.0
|
5 |
base_model: facebook/wav2vec2-large-xlsr-53
|
6 |
tags:
|
7 |
-
- automatic-speech-recognition
|
8 |
-
- common_voice
|
9 |
- generated_from_trainer
|
10 |
datasets:
|
11 |
- common_voice
|
@@ -18,15 +14,15 @@ model-index:
|
|
18 |
name: Automatic Speech Recognition
|
19 |
type: automatic-speech-recognition
|
20 |
dataset:
|
21 |
-
name:
|
22 |
type: common_voice
|
23 |
config: tr
|
24 |
split: test
|
25 |
-
args:
|
26 |
metrics:
|
27 |
- name: Wer
|
28 |
type: wer
|
29 |
-
value: 0.
|
30 |
---
|
31 |
|
32 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -34,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
34 |
|
35 |
# wav2vec2-common_voice-tr-demo
|
36 |
|
37 |
-
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the
|
38 |
It achieves the following results on the evaluation set:
|
39 |
-
- Loss: 0.
|
40 |
-
- Wer: 0.
|
41 |
|
42 |
## Model description
|
43 |
|
@@ -71,22 +67,22 @@ The following hyperparameters were used during training:
|
|
71 |
|
72 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
73 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
74 |
-
| No log | 0.92 | 100 | 3.
|
75 |
-
| No log | 1.83 | 200 | 3.
|
76 |
-
| No log | 2.75 | 300 | 0.
|
77 |
-
| No log | 3.67 | 400 | 0.
|
78 |
-
| 3.
|
79 |
-
| 3.
|
80 |
-
| 3.
|
81 |
-
| 3.
|
82 |
-
| 3.
|
83 |
-
| 0.
|
84 |
-
| 0.
|
85 |
-
| 0.
|
86 |
-
| 0.
|
87 |
-
| 0.
|
88 |
-
| 0.
|
89 |
-
| 0.
|
90 |
|
91 |
|
92 |
### Framework versions
|
|
|
1 |
---
|
|
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: facebook/wav2vec2-large-xlsr-53
|
4 |
tags:
|
|
|
|
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
- common_voice
|
|
|
14 |
name: Automatic Speech Recognition
|
15 |
type: automatic-speech-recognition
|
16 |
dataset:
|
17 |
+
name: common_voice
|
18 |
type: common_voice
|
19 |
config: tr
|
20 |
split: test
|
21 |
+
args: tr
|
22 |
metrics:
|
23 |
- name: Wer
|
24 |
type: wer
|
25 |
+
value: 0.3454192625880911
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
30 |
|
31 |
# wav2vec2-common_voice-tr-demo
|
32 |
|
33 |
+
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.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.3714
|
36 |
+
- Wer: 0.3454
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
67 |
|
68 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
69 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
70 |
+
| No log | 0.92 | 100 | 3.5988 | 1.0 |
|
71 |
+
| No log | 1.83 | 200 | 3.0083 | 0.9999 |
|
72 |
+
| No log | 2.75 | 300 | 0.8642 | 0.7579 |
|
73 |
+
| No log | 3.67 | 400 | 0.5713 | 0.6203 |
|
74 |
+
| 3.14 | 4.59 | 500 | 0.4795 | 0.5338 |
|
75 |
+
| 3.14 | 5.5 | 600 | 0.4441 | 0.4912 |
|
76 |
+
| 3.14 | 6.42 | 700 | 0.4241 | 0.4521 |
|
77 |
+
| 3.14 | 7.34 | 800 | 0.4326 | 0.4611 |
|
78 |
+
| 3.14 | 8.26 | 900 | 0.3913 | 0.4212 |
|
79 |
+
| 0.2183 | 9.17 | 1000 | 0.4036 | 0.3973 |
|
80 |
+
| 0.2183 | 10.09 | 1100 | 0.4035 | 0.3959 |
|
81 |
+
| 0.2183 | 11.01 | 1200 | 0.3807 | 0.3790 |
|
82 |
+
| 0.2183 | 11.93 | 1300 | 0.3750 | 0.3650 |
|
83 |
+
| 0.2183 | 12.84 | 1400 | 0.3822 | 0.3573 |
|
84 |
+
| 0.1011 | 13.76 | 1500 | 0.3747 | 0.3510 |
|
85 |
+
| 0.1011 | 14.68 | 1600 | 0.3714 | 0.3454 |
|
86 |
|
87 |
|
88 |
### Framework versions
|