Update README.md
Browse files
README.md
CHANGED
|
@@ -2,6 +2,8 @@
|
|
| 2 |
language: as
|
| 3 |
datasets:
|
| 4 |
- common_voice
|
|
|
|
|
|
|
| 5 |
tags:
|
| 6 |
- audio
|
| 7 |
- automatic-speech-recognition
|
|
@@ -64,7 +66,7 @@ wer = load_metric("wer")
|
|
| 64 |
processor = Wav2Vec2Processor.from_pretrained("manandey/wav2vec2-large-xlsr-assamese")
|
| 65 |
model = Wav2Vec2ForCTC.from_pretrained("manandey/wav2vec2-large-xlsr-assamese")
|
| 66 |
model.to("cuda")
|
| 67 |
-
chars_to_ignore_regex = '[
|
| 68 |
resampler = torchaudio.transforms.Resample(48_000, 16_000)
|
| 69 |
# Preprocessing the datasets.
|
| 70 |
# We need to read the aduio files as arrays
|
|
|
|
| 2 |
language: as
|
| 3 |
datasets:
|
| 4 |
- common_voice
|
| 5 |
+
metrics:
|
| 6 |
+
- wer
|
| 7 |
tags:
|
| 8 |
- audio
|
| 9 |
- automatic-speech-recognition
|
|
|
|
| 66 |
processor = Wav2Vec2Processor.from_pretrained("manandey/wav2vec2-large-xlsr-assamese")
|
| 67 |
model = Wav2Vec2ForCTC.from_pretrained("manandey/wav2vec2-large-xlsr-assamese")
|
| 68 |
model.to("cuda")
|
| 69 |
+
chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“\\%\\‘\\”\\�\\।\\']'
|
| 70 |
resampler = torchaudio.transforms.Resample(48_000, 16_000)
|
| 71 |
# Preprocessing the datasets.
|
| 72 |
# We need to read the aduio files as arrays
|