Update README.md
Browse files
README.md
CHANGED
|
@@ -40,8 +40,8 @@ from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
|
|
| 40 |
#Since marathi is not present on Common Voice, script for reading the below dataset can be picked up from the eval script below
|
| 41 |
mr_test_dataset = all_data['test']
|
| 42 |
|
| 43 |
-
processor = Wav2Vec2Processor.from_pretrained("
|
| 44 |
-
model = Wav2Vec2ForCTC.from_pretrained("
|
| 45 |
|
| 46 |
resampler = torchaudio.transforms.Resample(48_000, 16_000) #first arg - input sample, second arg - output sample
|
| 47 |
# Preprocessing the datasets. We need to read the aduio files as arrays
|
|
@@ -77,8 +77,8 @@ all_data = all_data.train_test_split(test_size=0.10,seed=2020) #seed number is i
|
|
| 77 |
mr_test_dataset = all_data['test']
|
| 78 |
wer = load_metric("wer")
|
| 79 |
|
| 80 |
-
processor = Wav2Vec2Processor.from_pretrained("
|
| 81 |
-
model = Wav2Vec2ForCTC.from_pretrained("
|
| 82 |
model.to("cuda")
|
| 83 |
|
| 84 |
chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“]'
|
|
|
|
| 40 |
#Since marathi is not present on Common Voice, script for reading the below dataset can be picked up from the eval script below
|
| 41 |
mr_test_dataset = all_data['test']
|
| 42 |
|
| 43 |
+
processor = Wav2Vec2Processor.from_pretrained("Tejas2000/SpeechRecog")
|
| 44 |
+
model = Wav2Vec2ForCTC.from_pretrained("Tejas2000/SpeechRecog")
|
| 45 |
|
| 46 |
resampler = torchaudio.transforms.Resample(48_000, 16_000) #first arg - input sample, second arg - output sample
|
| 47 |
# Preprocessing the datasets. We need to read the aduio files as arrays
|
|
|
|
| 77 |
mr_test_dataset = all_data['test']
|
| 78 |
wer = load_metric("wer")
|
| 79 |
|
| 80 |
+
processor = Wav2Vec2Processor.from_pretrained("Tejas2000/SpeechRecog")
|
| 81 |
+
model = Wav2Vec2ForCTC.from_pretrained("Tejas2000/SpeechRecog")
|
| 82 |
model.to("cuda")
|
| 83 |
|
| 84 |
chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“]'
|