Update README.md
Browse files
README.md
CHANGED
|
@@ -73,7 +73,16 @@ The model is available for use in the NeMo toolkit [3], and can be used as a pre
|
|
| 73 |
import nemo.collections.asr as nemo_asr
|
| 74 |
asr_model = nemo_asr.models.EncDecRNNTBPEModel.from_pretrained("nvidia/stt_be_conformer_transducer_large")
|
| 75 |
```
|
| 76 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 77 |
### Transcribing many audio files
|
| 78 |
|
| 79 |
```shell
|
|
|
|
| 73 |
import nemo.collections.asr as nemo_asr
|
| 74 |
asr_model = nemo_asr.models.EncDecRNNTBPEModel.from_pretrained("nvidia/stt_be_conformer_transducer_large")
|
| 75 |
```
|
| 76 |
+
### Transcribing using Python
|
| 77 |
+
First, let's get a sample
|
| 78 |
+
```
|
| 79 |
+
wget https://dldata-public.s3.us-east-2.amazonaws.com/2086-149220-0033.wav
|
| 80 |
+
```
|
| 81 |
+
Then simply do:
|
| 82 |
+
```
|
| 83 |
+
output = asr_model.transcribe(['2086-149220-0033.wav'])
|
| 84 |
+
print(output[0].text)
|
| 85 |
+
```
|
| 86 |
### Transcribing many audio files
|
| 87 |
|
| 88 |
```shell
|