fix random line in code
Browse files
README.md
CHANGED
@@ -45,13 +45,12 @@ For more information on how the model was trained, please take a look at the [of
|
|
45 |
To transcribe audio files the model can be used as a standalone acoustic model as follows:
|
46 |
​
|
47 |
```python
|
48 |
-
​
|
49 |
-
import torch
|
50 |
import torchaudio
|
51 |
from transformers import MCTCTForCTC, MCTCTProcessor
|
52 |
|
53 |
-
model = MCTCForCTC.from_pretrained("speechbrain/
|
54 |
-
processor = MCTCTProcessor.from_pretrained("speechbrain/
|
55 |
|
56 |
# load dummy dataset and read soundfiles
|
57 |
ds = load_dataset("patrickvonplaten/librispeech_asr_dummy", "clean", split="validation")
|
|
|
45 |
To transcribe audio files the model can be used as a standalone acoustic model as follows:
|
46 |
​
|
47 |
```python
|
48 |
+
​import torch
|
|
|
49 |
import torchaudio
|
50 |
from transformers import MCTCTForCTC, MCTCTProcessor
|
51 |
|
52 |
+
model = MCTCForCTC.from_pretrained("speechbrain/mctct-large")
|
53 |
+
processor = MCTCTProcessor.from_pretrained("speechbrain/mctct-large")
|
54 |
|
55 |
# load dummy dataset and read soundfiles
|
56 |
ds = load_dataset("patrickvonplaten/librispeech_asr_dummy", "clean", split="validation")
|