Commit
•
6750fe1
1
Parent(s):
0c60532
Update README.md
Browse files
README.md
CHANGED
|
@@ -32,7 +32,9 @@ model-index:
|
|
| 32 |
Fine-tuned facebook/wav2vec2-large-xlsr-53 on Hindi and Marathi using the OpenSLR SLR64 datasets. When using this model, make sure that your speech input is sampled at 16kHz.
|
| 33 |
|
| 34 |
## Installation
|
|
|
|
| 35 |
pip install git+https://github.com/huggingface/transformers.git datasets librosa torch==1.7.0 torchaudio==0.7.0 jiwer
|
|
|
|
| 36 |
|
| 37 |
## Eval dataset:
|
| 38 |
```bash
|
|
@@ -99,7 +101,7 @@ import re
|
|
| 99 |
test = Dataset.from_csv('test.csv')
|
| 100 |
|
| 101 |
|
| 102 |
-
chars_to_ignore_regex = '[
|
| 103 |
|
| 104 |
# Preprocessing the datasets.
|
| 105 |
# We need to read the audio files as arrays
|
|
@@ -139,7 +141,7 @@ import numpy as np
|
|
| 139 |
import re
|
| 140 |
from datasets import load_dataset
|
| 141 |
|
| 142 |
-
chars_to_ignore_regex = '[
|
| 143 |
|
| 144 |
# Preprocessing the datasets.
|
| 145 |
# We need to read the audio files as arrays
|
| 32 |
Fine-tuned facebook/wav2vec2-large-xlsr-53 on Hindi and Marathi using the OpenSLR SLR64 datasets. When using this model, make sure that your speech input is sampled at 16kHz.
|
| 33 |
|
| 34 |
## Installation
|
| 35 |
+
```bash
|
| 36 |
pip install git+https://github.com/huggingface/transformers.git datasets librosa torch==1.7.0 torchaudio==0.7.0 jiwer
|
| 37 |
+
```
|
| 38 |
|
| 39 |
## Eval dataset:
|
| 40 |
```bash
|
| 101 |
test = Dataset.from_csv('test.csv')
|
| 102 |
|
| 103 |
|
| 104 |
+
chars_to_ignore_regex = '[\\\\,\\\\?\\\\.\\\\!\\\\-\\\\;\\\\:\\\\"\\\\“\\\\%\\\\‘\\\\”\\\\�\\\\।]'
|
| 105 |
|
| 106 |
# Preprocessing the datasets.
|
| 107 |
# We need to read the audio files as arrays
|
| 141 |
import re
|
| 142 |
from datasets import load_dataset
|
| 143 |
|
| 144 |
+
chars_to_ignore_regex = '[\\\\,\\\\?\\\\.\\\\!\\\\-\\\\;\\\\:\\\\"\\\\“\\\\%\\\\‘\\\\”\\\\�\\\\।]'
|
| 145 |
|
| 146 |
# Preprocessing the datasets.
|
| 147 |
# We need to read the audio files as arrays
|