speechbrainteam
commited on
Commit
•
9cc14c0
1
Parent(s):
9bac9ef
Update README.md
Browse files
README.md
CHANGED
@@ -69,6 +69,9 @@ asr_model.transcribe_file("speechbrain/asr-transformer-aishell/example_mandarin.
|
|
69 |
### Inference on GPU
|
70 |
To perform inference on the GPU, add `run_opts={"device":"cuda"}` when calling the `from_hparams` method.
|
71 |
|
|
|
|
|
|
|
72 |
### Training
|
73 |
The model was trained with SpeechBrain (Commit hash: '986a2175').
|
74 |
To train it from scratch follow these steps:
|
|
|
69 |
### Inference on GPU
|
70 |
To perform inference on the GPU, add `run_opts={"device":"cuda"}` when calling the `from_hparams` method.
|
71 |
|
72 |
+
## Parallel Inference on a Batch
|
73 |
+
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.
|
74 |
+
|
75 |
### Training
|
76 |
The model was trained with SpeechBrain (Commit hash: '986a2175').
|
77 |
To train it from scratch follow these steps:
|