Commit
•
e58d273
1
Parent(s):
de9f2dc
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,51 +1,27 @@
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
language: cs
|
| 4 |
-
|
| 5 |
datasets:
|
| 6 |
-
|
| 7 |
- common_voice
|
| 8 |
-
|
| 9 |
tags:
|
| 10 |
-
|
| 11 |
- audio
|
| 12 |
-
|
| 13 |
- automatic-speech-recognition
|
| 14 |
-
|
| 15 |
- speech
|
| 16 |
-
|
| 17 |
- xlsr-fine-tuning-week
|
| 18 |
-
|
| 19 |
license: apache-2.0
|
| 20 |
-
|
| 21 |
model-index:
|
| 22 |
-
|
| 23 |
- name: wav2vec2-large-xlsr-53-Czech by Mehdi Hosseini Moghadam
|
| 24 |
-
|
| 25 |
results:
|
| 26 |
-
|
| 27 |
- task:
|
| 28 |
-
|
| 29 |
name: Speech Recognition
|
| 30 |
-
|
| 31 |
type: automatic-speech-recognition
|
| 32 |
-
|
| 33 |
dataset:
|
| 34 |
-
|
| 35 |
name: Common Voice cs
|
| 36 |
-
|
| 37 |
type: common_voice
|
| 38 |
-
|
| 39 |
args: cs
|
| 40 |
-
|
| 41 |
metrics:
|
| 42 |
-
|
| 43 |
- name: Test WER
|
| 44 |
-
|
| 45 |
type: wer
|
| 46 |
-
|
| 47 |
value: 27.047806
|
| 48 |
-
|
| 49 |
---
|
| 50 |
|
| 51 |
# wav2vec2-large-xlsr-53-Czech
|
|
@@ -130,7 +106,7 @@ model = Wav2Vec2ForCTC.from_pretrained("MehdiHosseiniMoghadam/wav2vec2-large-xls
|
|
| 130 |
|
| 131 |
model.to("cuda")
|
| 132 |
|
| 133 |
-
chars_to_ignore_regex = '[
|
| 134 |
|
| 135 |
resampler = torchaudio.transforms.Resample(48_000, 16_000)
|
| 136 |
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
language: cs
|
|
|
|
| 3 |
datasets:
|
|
|
|
| 4 |
- common_voice
|
|
|
|
| 5 |
tags:
|
|
|
|
| 6 |
- audio
|
|
|
|
| 7 |
- automatic-speech-recognition
|
|
|
|
| 8 |
- speech
|
|
|
|
| 9 |
- xlsr-fine-tuning-week
|
|
|
|
| 10 |
license: apache-2.0
|
|
|
|
| 11 |
model-index:
|
|
|
|
| 12 |
- name: wav2vec2-large-xlsr-53-Czech by Mehdi Hosseini Moghadam
|
|
|
|
| 13 |
results:
|
|
|
|
| 14 |
- task:
|
|
|
|
| 15 |
name: Speech Recognition
|
|
|
|
| 16 |
type: automatic-speech-recognition
|
|
|
|
| 17 |
dataset:
|
|
|
|
| 18 |
name: Common Voice cs
|
|
|
|
| 19 |
type: common_voice
|
|
|
|
| 20 |
args: cs
|
|
|
|
| 21 |
metrics:
|
|
|
|
| 22 |
- name: Test WER
|
|
|
|
| 23 |
type: wer
|
|
|
|
| 24 |
value: 27.047806
|
|
|
|
| 25 |
---
|
| 26 |
|
| 27 |
# wav2vec2-large-xlsr-53-Czech
|
|
|
|
| 106 |
|
| 107 |
model.to("cuda")
|
| 108 |
|
| 109 |
+
chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“\\%\\‘\\”\\�]'
|
| 110 |
|
| 111 |
resampler = torchaudio.transforms.Resample(48_000, 16_000)
|
| 112 |
|