Text-to-Speech
Fairseq
English
audio
patrickvonplaten commited on
Commit
c601f5d
1 Parent(s): afe8005

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -4,6 +4,7 @@ The following should work with fairseq's most up-to-date version in a google col
4
 
5
  ```python
6
  from fairseq.checkpoint_utils import load_model_ensemble_and_task_from_hf
 
7
 
8
  model_ensemble, cfg, task = load_model_ensemble_and_task_from_hf_hub(
9
  "facebook/fastspeech2-test", arg_overrides={"vocoder": "griffin_lim", "fp16": False}
@@ -31,8 +32,6 @@ generator = task.build_generator(model_ensemble, cfg)
31
  generation = generator.generate(model_ensemble[0], sample)
32
  waveform = generation[0]["waveform"]
33
 
34
- import IPython.display as ipd
35
-
36
  ipd.Audio(waveform, rate=task.sr)
37
  ```
38
 
 
4
 
5
  ```python
6
  from fairseq.checkpoint_utils import load_model_ensemble_and_task_from_hf
7
+ import IPython.display as ipd
8
 
9
  model_ensemble, cfg, task = load_model_ensemble_and_task_from_hf_hub(
10
  "facebook/fastspeech2-test", arg_overrides={"vocoder": "griffin_lim", "fp16": False}
 
32
  generation = generator.generate(model_ensemble[0], sample)
33
  waveform = generation[0]["waveform"]
34
 
 
 
35
  ipd.Audio(waveform, rate=task.sr)
36
  ```
37