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-53-eo
|
@@ -103,7 +103,7 @@ processor = Wav2Vec2Processor.from_pretrained("cpierse/wav2vec2-large-xlsr-53-es
|
|
103 |
model = Wav2Vec2ForCTC.from_pretrained("cpierse/wav2vec2-large-xlsr-53-esperanto")
|
104 |
model.to("cuda")
|
105 |
|
106 |
-
chars_to_ignore_regex = '[
|
107 |
resampler = torchaudio.transforms.Resample(48_000, 16_000)
|
108 |
|
109 |
# Preprocessing the datasets.
|
@@ -133,7 +133,7 @@ result = test_dataset.map(evaluate, batched=True, batch_size=8)
|
|
133 |
print("WER: {:2f}".format(100 * chunked_wer(predictions=result["pred_strings"], targets=result["sentence"],chunk_size=2000)))
|
134 |
```
|
135 |
|
136 |
-
**Test Result**:
|
137 |
|
138 |
|
139 |
## Training
|
|
|
23 |
metrics:
|
24 |
- name: Test WER
|
25 |
type: wer
|
26 |
+
value: 12.31
|
27 |
---
|
28 |
|
29 |
# Wav2Vec2-Large-XLSR-53-eo
|
|
|
103 |
model = Wav2Vec2ForCTC.from_pretrained("cpierse/wav2vec2-large-xlsr-53-esperanto")
|
104 |
model.to("cuda")
|
105 |
|
106 |
+
chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“\\%\\‘\\”\\�\\„\\«\\(\\»\\)\\’\\']'
|
107 |
resampler = torchaudio.transforms.Resample(48_000, 16_000)
|
108 |
|
109 |
# Preprocessing the datasets.
|
|
|
133 |
print("WER: {:2f}".format(100 * chunked_wer(predictions=result["pred_strings"], targets=result["sentence"],chunk_size=2000)))
|
134 |
```
|
135 |
|
136 |
+
**Test Result**: 12.31 %
|
137 |
|
138 |
|
139 |
## Training
|