Commit
•
dc0130a
1
Parent(s):
7663885
Update README.md
Browse files
README.md
CHANGED
|
@@ -63,6 +63,9 @@ asr_model.transcribe_file("speechbrain/asr-crdnn-commonvoice-it/example-it.wav")
|
|
| 63 |
### Inference on GPU
|
| 64 |
To perform inference on the GPU, add `run_opts={"device":"cuda"}` when calling the `from_hparams` method.
|
| 65 |
|
|
|
|
|
|
|
|
|
|
| 66 |
### Training
|
| 67 |
The model was trained with SpeechBrain (Commit hash: '986a2175').
|
| 68 |
To train it from scratch follow these steps:
|
|
|
|
| 63 |
### Inference on GPU
|
| 64 |
To perform inference on the GPU, add `run_opts={"device":"cuda"}` when calling the `from_hparams` method.
|
| 65 |
|
| 66 |
+
## Parallel Inference on a Batch
|
| 67 |
+
Please, [see this Colab notebook](https://colab.research.google.com/drive/1hX5ZI9S4jHIjahFCZnhwwQmFoGAi3tmu?usp=sharing) to figure out how to transcribe in parallel a batch of input sentences using a pre-trained model.
|
| 68 |
+
|
| 69 |
### Training
|
| 70 |
The model was trained with SpeechBrain (Commit hash: '986a2175').
|
| 71 |
To train it from scratch follow these steps:
|