Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- fr
|
4 |
+
license: apache-2.0
|
5 |
+
tags:
|
6 |
+
- automatic-speech-recognition
|
7 |
+
- mozilla-foundation/common_voice_8_0
|
8 |
+
- fr
|
9 |
+
- robust-speech-event
|
10 |
+
datasets:
|
11 |
+
- mozilla-foundation/common_voice_8_0
|
12 |
+
model-index:
|
13 |
+
- name: XLS-R-1B - French
|
14 |
+
results:
|
15 |
+
- task:
|
16 |
+
name: Automatic Speech Recognition
|
17 |
+
type: automatic-speech-recognition
|
18 |
+
dataset:
|
19 |
+
name: Common Voice 8
|
20 |
+
type: mozilla-foundation/common_voice_8_0
|
21 |
+
args: fr
|
22 |
+
metrics:
|
23 |
+
- name: Test WER (without LM)
|
24 |
+
type: wer
|
25 |
+
value: 15.405483405483406
|
26 |
+
- name: Test CER (without LM)
|
27 |
+
type: cer
|
28 |
+
value: 4.8773030225289137
|
29 |
+
- name: Test WER (with LM)
|
30 |
+
type: wer
|
31 |
+
value: 12.5
|
32 |
+
---
|
33 |
+
|
34 |
+
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_8_0 - FR dataset.
|
35 |
+
It achieves the following results on the evaluation set:
|
36 |
+
|
37 |
+
|
38 |
+
**Without LM**:
|
39 |
+
- Wer: 0.154
|
40 |
+
**With LM**:
|