Update README.md
Browse files
README.md
CHANGED
@@ -42,7 +42,7 @@ import torchaudio
|
|
42 |
from datasets import load_dataset
|
43 |
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
|
44 |
|
45 |
-
test_dataset = load_dataset("common_voice", "vi", split="test")
|
46 |
|
47 |
processor = Wav2Vec2Processor.from_pretrained("not-tanh/wav2vec2-large-xlsr-53-vietnamese")
|
48 |
model = Wav2Vec2ForCTC.from_pretrained("not-tanh/wav2vec2-large-xlsr-53-vietnamese")
|
@@ -71,7 +71,7 @@ print("Reference:", test_dataset["sentence"][:2])
|
|
71 |
|
72 |
## Evaluation
|
73 |
|
74 |
-
The model can be evaluated as follows on the
|
75 |
|
76 |
|
77 |
```python
|
@@ -124,6 +124,6 @@ print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"],
|
|
124 |
## Training
|
125 |
## TODO
|
126 |
|
127 |
-
The Common Voice `train`, `validation`, and
|
128 |
|
129 |
-
The script used for training can be found ... # TODO
|
|
|
42 |
from datasets import load_dataset
|
43 |
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
|
44 |
|
45 |
+
test_dataset = load_dataset("common_voice", "vi", split="test")
|
46 |
|
47 |
processor = Wav2Vec2Processor.from_pretrained("not-tanh/wav2vec2-large-xlsr-53-vietnamese")
|
48 |
model = Wav2Vec2ForCTC.from_pretrained("not-tanh/wav2vec2-large-xlsr-53-vietnamese")
|
|
|
71 |
|
72 |
## Evaluation
|
73 |
|
74 |
+
The model can be evaluated as follows on the Vietnamese test data of Common Voice.
|
75 |
|
76 |
|
77 |
```python
|
|
|
124 |
## Training
|
125 |
## TODO
|
126 |
|
127 |
+
The Common Voice `train`, `validation`, the VIVOS and FOSD datasets were used for training
|
128 |
|
129 |
+
The script used for training can be found ... # TODO
|