Upload 4 files

app.py

@@ -33,19 +33,11 @@ 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.
-    The model has been trained on 8-second videos. Using much longer or shorter videos will degrade performance. Around 5s~12s should be fine.
-    """,
+    Code: <a href="https://github.com/acappemin/DeepAudio-V1">https://github.com/acappemin/DeepAudio-V1</a><br>
+    """
     inputs=[
         gr.Video(),
         gr.Text(label='Prompt'),
-        gr.Text(label='Negative prompt', value='music'),
-        gr.Number(label='Seed (-1: random)', value=-1, precision=0, minimum=-1),
-        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='playable_video',
     cache_examples=False,
@@ -53,12 +45,7 @@ video_to_audio_tab = gr.Interface(
     examples=[
         [
             'https://huggingface.co/hkchengrex/MMAudio/resolve/main/examples/sora_beach.mp4',
-            'waves, seagulls',
             '',
-            0,
-            25,
-            4.5,
-            10,
         ],
     ])
 

tts.sh

@@ -1 +1 @@
-python ./F5-TTS/src/f5_tts/infer/infer_cli_tts_test.py --output_dir ./tests/outputs_tts/ --start 0 --end 10 --ckpt_file ./F5-TTS/ckpts/v2c/v2c_l44.pt --infer_list ./tests/tts_test.lst
+python ./F5-TTS/src/f5_tts/infer/infer_cli_tts_test.py --output_dir ./tests/outputs_tts/ --start 0 --end 10 --ckpt_file ./F5-TTS/ckpts/v2c/v2c_l44.pt --infer_list ./tests/tts_test.lst

v2a.sh

@@ -1,2 +1,2 @@
-cd ./MMAudio
-python ./demo.py --output ../tests/outputs_v2a_l44_test/ --start 0 --end 10 --scp ../tests/test.scp --calc_energy 1
+cd ./MMAudio
+python ./demo.py --output ../tests/outputs_v2a_l44_test/ --start 0 --end 10 --scp ../tests/test.scp --calc_energy 1