Update app.py

app.py

@@ -98,47 +98,9 @@ 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
-
-
 video_to_audio_tab = gr.Interface(
     fn=video_to_audio,
-    description="""
-    Project page: <a href="https://hkchengrex.com/MMAudio/">https://hkchengrex.com/MMAudio/</a><br>
-    Code: <a href="https://github.com/hkchengrex/MMAudio">https://github.com/hkchengrex/MMAudio</a><br>
 
-    NOTE: It takes longer to process high-resolution videos (>384 px on the shorter side). 
-    Doing so does not improve results.
-    """,
     inputs=[
         gr.Video(),
         gr.Text(label='Prompt'),
@@ -149,124 +111,7 @@ video_to_audio_tab = gr.Interface(
         gr.Number(label='Duration (sec)', value=8, minimum=1),
     ],
     outputs='playable_video',
-    cache_examples=False,
-    title='MMAudio — Video-to-Audio Synthesis',
-    examples=[
-        [
-            'https://huggingface.co/hkchengrex/MMAudio/resolve/main/examples/sora_beach.mp4',
-            'waves, seagulls',
-            '',
-            0,
-            25,
-            4.5,
-            10,
-        ],
-        [
-            'https://huggingface.co/hkchengrex/MMAudio/resolve/main/examples/sora_serpent.mp4',
-            '',
-            'music',
-            0,
-            25,
-            4.5,
-            10,
-        ],
-        [
-            'https://huggingface.co/hkchengrex/MMAudio/resolve/main/examples/sora_seahorse.mp4',
-            'bubbles',
-            '',
-            0,
-            25,
-            4.5,
-            10,
-        ],
-        [
-            'https://huggingface.co/hkchengrex/MMAudio/resolve/main/examples/sora_india.mp4',
-            'Indian holy music',
-            '',
-            0,
-            25,
-            4.5,
-            10,
-        ],
-        [
-            'https://huggingface.co/hkchengrex/MMAudio/resolve/main/examples/sora_galloping.mp4',
-            'galloping',
-            '',
-            0,
-            25,
-            4.5,
-            10,
-        ],
-        [
-            'https://huggingface.co/hkchengrex/MMAudio/resolve/main/examples/sora_kraken.mp4',
-            'waves, storm',
-            '',
-            0,
-            25,
-            4.5,
-            10,
-        ],
-        [
-            'https://huggingface.co/hkchengrex/MMAudio/resolve/main/examples/sora_nyc.mp4',
-            '',
-            '',
-            0,
-            25,
-            4.5,
-            10,
-        ],
-        [
-            'https://huggingface.co/hkchengrex/MMAudio/resolve/main/examples/mochi_storm.mp4',
-            'storm',
-            '',
-            0,
-            25,
-            4.5,
-            10,
-        ],
-        [
-            'https://huggingface.co/hkchengrex/MMAudio/resolve/main/examples/hunyuan_spring.mp4',
-            '',
-            '',
-            0,
-            25,
-            4.5,
-            10,
-        ],
-        [
-            'https://huggingface.co/hkchengrex/MMAudio/resolve/main/examples/hunyuan_typing.mp4',
-            'typing',
-            '',
-            0,
-            25,
-            4.5,
-            10,
-        ],
-        [
-            'https://huggingface.co/hkchengrex/MMAudio/resolve/main/examples/hunyuan_wake_up.mp4',
-            '',
-            '',
-            0,
-            25,
-            4.5,
-            10,
-        ],
-    ])
 
-text_to_audio_tab = gr.Interface(
-    fn=text_to_audio,
-    inputs=[
-        gr.Text(label='Prompt'),
-        gr.Text(label='Negative prompt'),
-        gr.Number(label='Seed', value=0, precision=0, minimum=0),
-        gr.Number(label='Num steps', value=25, precision=0, minimum=1),
-        gr.Number(label='Guidance Strength', value=4.5, minimum=1),
-        gr.Number(label='Duration (sec)', value=8, minimum=1),
-    ],
-    outputs='audio',
-    cache_examples=False,
-    title='MMAudio — Text-to-Audio Synthesis',
-)
 
 if __name__ == "__main__":
     gr.TabbedInterface([video_to_audio_tab, text_to_audio_tab],