Fix usage code blocks.

#58
by bezzam HF Staff - opened
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -88,7 +88,7 @@ synthesiser = pipeline("text-to-speech", "suno/bark")
88
 
89
  speech = synthesiser("Hello, my dog is cooler than you!", forward_params={"do_sample": True})
90
 
91
- scipy.io.wavfile.write("bark_out.wav", rate=speech["sampling_rate"], data=speech["audio"])
92
  ```
93
 
94
  3. Run inference via the Transformers modelling code. You can use the processor + generate code to convert text into a mono 24 kHz speech waveform for more fine-grained control.
@@ -121,7 +121,7 @@ Or save them as a `.wav` file using a third-party library, e.g. `scipy`:
121
  ```python
122
  import scipy
123
 
124
- sampling_rate = model.config.sample_rate
125
  scipy.io.wavfile.write("bark_out.wav", rate=sampling_rate, data=speech_values.cpu().numpy().squeeze())
126
  ```
127
 
 
88
 
89
  speech = synthesiser("Hello, my dog is cooler than you!", forward_params={"do_sample": True})
90
 
91
+ scipy.io.wavfile.write("bark_out.wav", rate=speech["sampling_rate"], data=speech["audio"].squeeze())
92
  ```
93
 
94
  3. Run inference via the Transformers modelling code. You can use the processor + generate code to convert text into a mono 24 kHz speech waveform for more fine-grained control.
 
121
  ```python
122
  import scipy
123
 
124
+ sampling_rate = model.generation_config.sample_rate
125
  scipy.io.wavfile.write("bark_out.wav", rate=sampling_rate, data=speech_values.cpu().numpy().squeeze())
126
  ```
127