lucas-meyer
commited on
Commit
•
2ceed36
1
Parent(s):
9fd2d38
Update README.md
Browse files
README.md
CHANGED
@@ -5,33 +5,21 @@ tags:
|
|
5 |
metrics:
|
6 |
- wer
|
7 |
model-index:
|
8 |
-
- name: xls-r-asr_xh-
|
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 |
-
# xls-r-asr_xh-
|
16 |
|
17 |
-
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on
|
18 |
-
It achieves the following results
|
19 |
-
-
|
20 |
-
- Wer:
|
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 |
|
@@ -50,7 +38,7 @@ The following hyperparameters were used during training:
|
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
-
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
55 |
| 10.217 | 0.64 | 100 | 4.3372 | 1.0 |
|
56 |
| 3.5916 | 1.27 | 200 | 3.0758 | 1.0 |
|
@@ -73,4 +61,4 @@ The following hyperparameters were used during training:
|
|
73 |
- Transformers 4.28.0
|
74 |
- Pytorch 2.0.1+cu117
|
75 |
- Datasets 2.14.4
|
76 |
-
- Tokenizers 0.13.3
|
|
|
5 |
metrics:
|
6 |
- wer
|
7 |
model-index:
|
8 |
+
- name: xls-r-asr_xh-run6
|
9 |
results: []
|
10 |
+
datasets:
|
11 |
+
- lucas-meyer/asr_xh
|
12 |
---
|
13 |
|
14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
should probably proofread and complete it, then remove this comment. -->
|
16 |
|
17 |
+
# xls-r-asr_xh-run6
|
18 |
|
19 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the asr_xh dataset.
|
20 |
+
It achieves the following results:
|
21 |
+
- Wer (Validation): 53.06%
|
22 |
+
- Wer (Test): 53.88%
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
|
24 |
### Training hyperparameters
|
25 |
|
|
|
38 |
|
39 |
### Training results
|
40 |
|
41 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer (Train) |
|
42 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
43 |
| 10.217 | 0.64 | 100 | 4.3372 | 1.0 |
|
44 |
| 3.5916 | 1.27 | 200 | 3.0758 | 1.0 |
|
|
|
61 |
- Transformers 4.28.0
|
62 |
- Pytorch 2.0.1+cu117
|
63 |
- Datasets 2.14.4
|
64 |
+
- Tokenizers 0.13.3
|