Update README.md
Browse files
README.md
CHANGED
@@ -40,7 +40,7 @@ import torchaudio
|
|
40 |
from datasets import load_dataset
|
41 |
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
|
42 |
|
43 |
-
test_dataset = load_dataset("csv", data_files={"test": "/content/test.csv"}, delimiter="
|
44 |
|
45 |
processor = Wav2Vec2Processor.from_pretrained("csikasote/wav2vec2-large-xlsr-bemba")
|
46 |
model = Wav2Vec2ForCTC.from_pretrained("csikasote/wav2vec2-large-xlsr-bemba")
|
@@ -86,7 +86,7 @@ processor = Wav2Vec2Processor.from_pretrained("csikasote/wav2vec2-large-xlsr-bem
|
|
86 |
model = Wav2Vec2ForCTC.from_pretrained("csikasote/wav2vec2-large-xlsr-bemba")
|
87 |
model.to("cuda")
|
88 |
|
89 |
-
chars_to_ignore_regex = '[
|
90 |
#resampler = torchaudio.transforms.Resample(48_000, 16_000)
|
91 |
|
92 |
# Preprocessing the datasets.
|
|
|
40 |
from datasets import load_dataset
|
41 |
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
|
42 |
|
43 |
+
test_dataset = load_dataset("csv", data_files={"test": "/content/test.csv"}, delimiter="\\\\t")["test"] # Adapt the path to test.csv
|
44 |
|
45 |
processor = Wav2Vec2Processor.from_pretrained("csikasote/wav2vec2-large-xlsr-bemba")
|
46 |
model = Wav2Vec2ForCTC.from_pretrained("csikasote/wav2vec2-large-xlsr-bemba")
|
|
|
86 |
model = Wav2Vec2ForCTC.from_pretrained("csikasote/wav2vec2-large-xlsr-bemba")
|
87 |
model.to("cuda")
|
88 |
|
89 |
+
chars_to_ignore_regex = '[\,\?\.\!\;\:\"\“]'
|
90 |
#resampler = torchaudio.transforms.Resample(48_000, 16_000)
|
91 |
|
92 |
# Preprocessing the datasets.
|