patrickvonplaten
commited on
Commit
•
9fdc306
1
Parent(s):
e331f22
Update README.md
Browse files
README.md
CHANGED
@@ -23,7 +23,7 @@ model-index:
|
|
23 |
metrics:
|
24 |
- name: Test WER
|
25 |
type: wer
|
26 |
-
value:
|
27 |
---
|
28 |
|
29 |
# Wav2Vec2-Large-XLSR-Indonesian
|
@@ -86,7 +86,7 @@ processor = Wav2Vec2Processor.from_pretrained("Galuh/wav2vec2-large-xlsr-indones
|
|
86 |
model = Wav2Vec2ForCTC.from_pretrained("Galuh/wav2vec2-large-xlsr-indonesian")
|
87 |
model.to("cuda")
|
88 |
|
89 |
-
chars_to_ignore_regex = '[
|
90 |
|
91 |
resampler = torchaudio.transforms.Resample(48_000, 16_000)
|
92 |
|
@@ -117,7 +117,7 @@ result = test_dataset.map(evaluate, batched=True, batch_size=8)
|
|
117 |
print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
|
118 |
```
|
119 |
|
120 |
-
**Test Result**:
|
121 |
|
122 |
## Training
|
123 |
|
|
|
23 |
metrics:
|
24 |
- name: Test WER
|
25 |
type: wer
|
26 |
+
value: 21.07
|
27 |
---
|
28 |
|
29 |
# Wav2Vec2-Large-XLSR-Indonesian
|
|
|
86 |
model = Wav2Vec2ForCTC.from_pretrained("Galuh/wav2vec2-large-xlsr-indonesian")
|
87 |
model.to("cuda")
|
88 |
|
89 |
+
chars_to_ignore_regex = '[\\\\\\\\,\\\\\\\\?\\\\\\\\.\\\\\\\\!\\\\\\\\-\\\\\\\\;\\\\\\\\:\\\\\\\\"\\\\\\\\“]'
|
90 |
|
91 |
resampler = torchaudio.transforms.Resample(48_000, 16_000)
|
92 |
|
|
|
117 |
print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
|
118 |
```
|
119 |
|
120 |
+
**Test Result**: 21.07 %
|
121 |
|
122 |
## Training
|
123 |
|