patrickvonplaten
commited on
Commit
•
02e1910
1
Parent(s):
88ef861
Update README.md
Browse files
README.md
CHANGED
@@ -6,11 +6,41 @@ tags:
|
|
6 |
- automatic-speech-recognition
|
7 |
- mozilla-foundation/common_voice_8_0
|
8 |
- generated_from_trainer
|
|
|
|
|
9 |
datasets:
|
10 |
-
-
|
11 |
model-index:
|
12 |
-
- name:
|
13 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
---
|
15 |
|
16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -93,6 +123,19 @@ The following hyperparameters were used during training:
|
|
93 |
| 1.0396 | 47.94 | 17500 | 0.2788 | 0.2525 |
|
94 |
| 1.0481 | 49.31 | 18000 | 0.2777 | 0.2534 |
|
95 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
96 |
|
97 |
### Framework versions
|
98 |
|
|
|
6 |
- automatic-speech-recognition
|
7 |
- mozilla-foundation/common_voice_8_0
|
8 |
- generated_from_trainer
|
9 |
+
- sv
|
10 |
+
- robust-speech-event
|
11 |
datasets:
|
12 |
+
- mozilla-foundation/common_voice_8_0
|
13 |
model-index:
|
14 |
+
- name: XLS-R-300M - Swedish - CV8 - v2
|
15 |
+
results:
|
16 |
+
- task:
|
17 |
+
name: Automatic Speech Recognition
|
18 |
+
type: automatic-speech-recognition
|
19 |
+
dataset:
|
20 |
+
name: Common Voice 8
|
21 |
+
type: mozilla-foundation/common_voice_8_0
|
22 |
+
args: sv-SE
|
23 |
+
metrics:
|
24 |
+
- name: Test WER
|
25 |
+
type: wer
|
26 |
+
value: 17.33
|
27 |
+
- name: Test CER
|
28 |
+
type: cer
|
29 |
+
value: 5.8
|
30 |
+
- task:
|
31 |
+
name: Automatic Speech Recognition
|
32 |
+
type: automatic-speech-recognition
|
33 |
+
dataset:
|
34 |
+
name: Robust Speech Event - Dev Data
|
35 |
+
type: speech-recognition-community-v2/dev_data
|
36 |
+
args: sv
|
37 |
+
metrics:
|
38 |
+
- name: Test WER
|
39 |
+
type: wer
|
40 |
+
value: 27.01
|
41 |
+
- name: Test CER
|
42 |
+
type: cer
|
43 |
+
value: 12.92
|
44 |
---
|
45 |
|
46 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
123 |
| 1.0396 | 47.94 | 17500 | 0.2788 | 0.2525 |
|
124 |
| 1.0481 | 49.31 | 18000 | 0.2777 | 0.2534 |
|
125 |
|
126 |
+
### Evaluation Commands
|
127 |
+
|
128 |
+
1. To evaluate on `mozilla-foundation/common_voice_7_0` with split `test`
|
129 |
+
|
130 |
+
```bash
|
131 |
+
python eval.py --model_id patrickvonplaten/xls-r-300m-sv-cv8 --dataset mozilla-foundation/common_voice_8_0 --config sv-SE --split test
|
132 |
+
```
|
133 |
+
|
134 |
+
2. To evaluate on `speech-recognition-community-v2/dev_data`
|
135 |
+
|
136 |
+
```bash
|
137 |
+
python eval.py --model_id patrickvonplaten/xls-r-300m-sv-cv8 --dataset speech-recognition-community-v2/dev_data --config sv --split validation --chunk_length_s 5.0 --stride_length_s 1.0
|
138 |
+
```
|
139 |
|
140 |
### Framework versions
|
141 |
|