Duration 20s

app.py

@@ -58,6 +58,7 @@ class Tango:
     def generate(self, prompt, steps = 100, guidance = 3, samples = 1, disable_progress = True):
         # Generate audio for a single prompt string
         with torch.no_grad():
+            self.model.set_generation_params(duration=20)
             latents = self.model.inference([prompt], self.scheduler, steps, guidance, samples, disable_progress = disable_progress)
             mel = self.vae.decode_first_stage(latents)
             wave = self.vae.decode_to_waveform(mel)