Update README.md
Browse files
README.md
CHANGED
|
@@ -1,7 +1,9 @@
|
|
| 1 |
---
|
| 2 |
language: as
|
| 3 |
datasets:
|
| 4 |
-
- common_voice
|
|
|
|
|
|
|
| 5 |
tags:
|
| 6 |
- audio
|
| 7 |
- automatic-speech-recognition
|
|
@@ -23,7 +25,6 @@ model-index:
|
|
| 23 |
type: wer
|
| 24 |
value: 74.25
|
| 25 |
---
|
| 26 |
-
|
| 27 |
# Wav2Vec2-Large-XLSR-53-Assamese
|
| 28 |
|
| 29 |
Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) in Assamese using the [Common Voice](https://huggingface.co/datasets/common_voice)
|
|
@@ -78,7 +79,7 @@ chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\‘\”\�\'\।]'
|
|
| 78 |
resampler = torchaudio.transforms.Resample(48_000, 16_000)
|
| 79 |
|
| 80 |
# Preprocessing the datasets.
|
| 81 |
-
# We need to read the
|
| 82 |
|
| 83 |
def speech_file_to_array_fn(batch):
|
| 84 |
batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
|
|
|
|
| 1 |
---
|
| 2 |
language: as
|
| 3 |
datasets:
|
| 4 |
+
- common_voice
|
| 5 |
+
metrics:
|
| 6 |
+
- wer
|
| 7 |
tags:
|
| 8 |
- audio
|
| 9 |
- automatic-speech-recognition
|
|
|
|
| 25 |
type: wer
|
| 26 |
value: 74.25
|
| 27 |
---
|
|
|
|
| 28 |
# Wav2Vec2-Large-XLSR-53-Assamese
|
| 29 |
|
| 30 |
Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) in Assamese using the [Common Voice](https://huggingface.co/datasets/common_voice)
|
|
|
|
| 79 |
resampler = torchaudio.transforms.Resample(48_000, 16_000)
|
| 80 |
|
| 81 |
# Preprocessing the datasets.
|
| 82 |
+
# We need to read the audio files as arrays
|
| 83 |
|
| 84 |
def speech_file_to_array_fn(batch):
|
| 85 |
batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
|