Update README.md
Browse files
README.md
CHANGED
@@ -7,6 +7,7 @@ tags:
|
|
7 |
- automatic-speech-recognition
|
8 |
- speech
|
9 |
- xlsr-fine-tuning-week
|
|
|
10 |
license: apache-2.0
|
11 |
model-index:
|
12 |
- name: XLSR Wav2Vec2 for 56 language by Voidful
|
@@ -17,6 +18,10 @@ model-index:
|
|
17 |
dataset:
|
18 |
name: Common Voice
|
19 |
type: common_voice
|
|
|
|
|
|
|
|
|
20 |
---
|
21 |
|
22 |
# wav2vec2-xlsr-multilingual-56
|
@@ -124,7 +129,6 @@ predict(load_file_to_data('audio file path',sampling_rate=16_000)) # beware of t
|
|
124 |
predict_lang_specific(load_file_to_data('audio file path',sampling_rate=16_000),'en') # beware of the audio file sampling rate
|
125 |
|
126 |
```
|
127 |
-
|
128 |
## Result
|
129 |
| Common Voice Languages | Num. of data | Hour | WER | CER |
|
130 |
|------------------------|--------------|--------|--------|-------|
|
|
|
7 |
- automatic-speech-recognition
|
8 |
- speech
|
9 |
- xlsr-fine-tuning-week
|
10 |
+
- robust-speech-event
|
11 |
license: apache-2.0
|
12 |
model-index:
|
13 |
- name: XLSR Wav2Vec2 for 56 language by Voidful
|
|
|
18 |
dataset:
|
19 |
name: Common Voice
|
20 |
type: common_voice
|
21 |
+
metrics:
|
22 |
+
- name: Test CER
|
23 |
+
type: cer
|
24 |
+
value: 23.21
|
25 |
---
|
26 |
|
27 |
# wav2vec2-xlsr-multilingual-56
|
|
|
129 |
predict_lang_specific(load_file_to_data('audio file path',sampling_rate=16_000),'en') # beware of the audio file sampling rate
|
130 |
|
131 |
```
|
|
|
132 |
## Result
|
133 |
| Common Voice Languages | Num. of data | Hour | WER | CER |
|
134 |
|------------------------|--------------|--------|--------|-------|
|