bofenghuang
commited on
Commit
•
6721a6f
1
Parent(s):
6e1a7c6
updt evaluation
Browse files
README.md
CHANGED
@@ -6,17 +6,39 @@ tags:
|
|
6 |
- automatic-speech-recognition
|
7 |
- mozilla-foundation/common_voice_9_0
|
8 |
- generated_from_trainer
|
|
|
|
|
9 |
datasets:
|
10 |
-
- common_voice_9_0
|
11 |
model-index:
|
12 |
-
- name: wav2vec2-xls-r-1b-ft
|
13 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
---
|
15 |
|
16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
should probably proofread and complete it, then remove this comment. -->
|
18 |
|
19 |
-
# wav2vec2-xls-r-1b-ft
|
20 |
|
21 |
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on the MOZILLA-FOUNDATION/COMMON_VOICE_9_0 - FR dataset.
|
22 |
It achieves the following results on the evaluation set:
|
|
|
6 |
- automatic-speech-recognition
|
7 |
- mozilla-foundation/common_voice_9_0
|
8 |
- generated_from_trainer
|
9 |
+
- hf-asr-leaderboard
|
10 |
+
- robust-speech-event
|
11 |
datasets:
|
12 |
+
- mozilla-foundation/common_voice_9_0
|
13 |
model-index:
|
14 |
+
- name: wav2vec2-xls-r-1b-ft
|
15 |
+
results:
|
16 |
+
- task:
|
17 |
+
name: Automatic Speech Recognition
|
18 |
+
type: automatic-speech-recognition
|
19 |
+
dataset:
|
20 |
+
name: Common Voice 9
|
21 |
+
type: mozilla-foundation/common_voice_9_0
|
22 |
+
args: fr
|
23 |
+
metrics:
|
24 |
+
- name: Test WER
|
25 |
+
type: wer
|
26 |
+
value: 12.72
|
27 |
+
- name: Test CER
|
28 |
+
type: cer
|
29 |
+
value: 3.78
|
30 |
+
- name: Test WER (+LM)
|
31 |
+
type: wer
|
32 |
+
value: 10.60
|
33 |
+
- name: Test CER (+LM)
|
34 |
+
type: cer
|
35 |
+
value: 3.41
|
36 |
---
|
37 |
|
38 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
39 |
should probably proofread and complete it, then remove this comment. -->
|
40 |
|
41 |
+
# wav2vec2-xls-r-1b-ft
|
42 |
|
43 |
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on the MOZILLA-FOUNDATION/COMMON_VOICE_9_0 - FR dataset.
|
44 |
It achieves the following results on the evaluation set:
|