fix

app.py

@@ -98,36 +98,36 @@ def video_to_audio(video: gr.Video, prompt: str, negative_prompt: str, seed: int
     return video_save_path
 
 
-# @spaces.GPU(duration=120)
-# @torch.inference_mode()
-# def text_to_audio(prompt: str, negative_prompt: str, seed: int, num_steps: int, cfg_strength: float,
-#                   duration: float):
-
-#     rng = torch.Generator(device=device)
-#     if seed >= 0:
-#         rng.manual_seed(seed)
-#     else:
-#         rng.seed()
-#     fm = FlowMatching(min_sigma=0, inference_mode='euler', num_steps=num_steps)
-
-#     clip_frames = sync_frames = None
-#     seq_cfg.duration = duration
-#     net.update_seq_lengths(seq_cfg.latent_seq_len, seq_cfg.clip_seq_len, seq_cfg.sync_seq_len)
-
-#     audios = generate(clip_frames,
-#                       sync_frames, [prompt],
-#                       negative_text=[negative_prompt],
-#                       feature_utils=feature_utils,
-#                       net=net,
-#                       fm=fm,
-#                       rng=rng,
-#                       cfg_strength=cfg_strength)
-#     audio = audios.float().cpu()[0]
-
-#     audio_save_path = tempfile.NamedTemporaryFile(delete=False, suffix='.flac').name
-#     torchaudio.save(audio_save_path, audio, seq_cfg.sampling_rate)
-#     log.info(f'Saved audio to {audio_save_path}')
-#     return audio_save_path
+@spaces.GPU(duration=120)
+@torch.inference_mode()
+def text_to_audio(prompt: str, negative_prompt: str, seed: int, num_steps: int, cfg_strength: float,
+                  duration: float):
+
+    rng = torch.Generator(device=device)
+    if seed >= 0:
+        rng.manual_seed(seed)
+    else:
+        rng.seed()
+    fm = FlowMatching(min_sigma=0, inference_mode='euler', num_steps=num_steps)
+
+    clip_frames = sync_frames = None
+    seq_cfg.duration = duration
+    net.update_seq_lengths(seq_cfg.latent_seq_len, seq_cfg.clip_seq_len, seq_cfg.sync_seq_len)
+
+    audios = generate(clip_frames,
+                      sync_frames, [prompt],
+                      negative_text=[negative_prompt],
+                      feature_utils=feature_utils,
+                      net=net,
+                      fm=fm,
+                      rng=rng,
+                      cfg_strength=cfg_strength)
+    audio = audios.float().cpu()[0]
+
+    audio_save_path = tempfile.NamedTemporaryFile(delete=False, suffix='.flac').name
+    torchaudio.save(audio_save_path, audio, seq_cfg.sampling_rate)
+    log.info(f'Saved audio to {audio_save_path}')
+    return audio_save_path
 
 
 video_to_audio_tab = gr.Interface(