Update README.md
Browse files
README.md
CHANGED
@@ -77,14 +77,14 @@ from datasets import load_dataset, load_metric
|
|
77 |
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
|
78 |
import re
|
79 |
|
80 |
-
test_dataset = load_dataset("common_voice", "
|
81 |
wer = load_metric("wer")
|
82 |
|
83 |
processor = Wav2Vec2Processor.from_pretrained("mrm8488/wav2vec2-large-xlsr-53-euskera")
|
84 |
model = Wav2Vec2ForCTC.from_pretrained("mrm8488/wav2vec2-large-xlsr-53-euskera")
|
85 |
model.to("cuda")
|
86 |
|
87 |
-
chars_to_ignore_regex = '[
|
88 |
resampler = torchaudio.transforms.Resample(48_000, 16_000)
|
89 |
|
90 |
# Preprocessing the datasets.
|
|
|
77 |
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
|
78 |
import re
|
79 |
|
80 |
+
test_dataset = load_dataset("common_voice", "eu", split="test")
|
81 |
wer = load_metric("wer")
|
82 |
|
83 |
processor = Wav2Vec2Processor.from_pretrained("mrm8488/wav2vec2-large-xlsr-53-euskera")
|
84 |
model = Wav2Vec2ForCTC.from_pretrained("mrm8488/wav2vec2-large-xlsr-53-euskera")
|
85 |
model.to("cuda")
|
86 |
|
87 |
+
chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“\\%\\‘\\”\\�]'
|
88 |
resampler = torchaudio.transforms.Resample(48_000, 16_000)
|
89 |
|
90 |
# Preprocessing the datasets.
|