feat(gc): Added vocal volume

app-full.py

@@ -104,7 +104,7 @@ def cut_vocal_and_inst(yt_url):
         print(result.stdout.decode())
         return ("/content/rvc-models/separated/htdemucs/audio/vocals.wav", "/content/rvc-models/separated/htdemucs/audio/no_vocals.wav", yt_audio_path, "/content/rvc-models/separated/htdemucs/audio/vocals.wav")
 
-def combine_vocal_and_inst(audio_data):
+def combine_vocal_and_inst(audio_data, audio_volume):
     print(audio_data)
     if not os.path.exists("/content/result"):
         os.mkdir("/content/result")
@@ -116,7 +116,7 @@ def combine_vocal_and_inst(audio_data):
         wave_file.setsampwidth(2)
         wave_file.setframerate(audio_data[0])
         wave_file.writeframes(audio_data[1].tobytes())
-    command =  f'ffmpeg -y -i {inst_path} -i {vocal_path} -filter_complex [1:a]volume=6dB[v];[0:a][v]amix=inputs=2:duration=longest -b:a 320k -c:a libmp3lame {output_path}'
+    command =  f'ffmpeg -y -i {inst_path} -i {vocal_path} -filter_complex [1:a]volume={audio_volume}dB[v];[0:a][v]amix=inputs=2:duration=longest -b:a 320k -c:a libmp3lame {output_path}'
     result = subprocess.run(command.split(), stdout=subprocess.PIPE)
     return output_path
 
@@ -181,6 +181,7 @@ if __name__ == '__main__':
         gr.Markdown(
             "# <center> RVC Models\n"
             "## <center> The input audio should be clean and pure voice without background music.\n"
+            "### <center> More feature will be added soon... \n"
             "![visitor badge](https://visitor-badge.glitch.me/badge?page_id=ArkanDash.Rvc-Models)\n\n"
             "[![image](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1hx6kKvIuv5XNY1Gai2PEuZhpO5z6xpVh?usp=sharing)\n\n"
             "[![Original Repo](https://badgen.net/badge/icon/github?icon=github&label=Original%20Repo)](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI)"
@@ -227,14 +228,23 @@ if __name__ == '__main__':
                             tts_text = gr.Textbox(visible=False,label="TTS text (100 words limitation)" if limitation else "TTS text")
                             tts_voice = gr.Dropdown(label="Edge-tts speaker", choices=voices, visible=False, allow_custom_value=False, value="en-US-AnaNeural-Female")
                             vc_submit = gr.Button("Generate", variant="primary")
-                        with gr.Column():
                             vc_output1 = gr.Textbox(label="Output Message")
                             vc_output2 = gr.Audio(label="Output Audio")
-                            vc_combine =  gr.Button("Combine",variant="primary")
-                            vc_outputCombine = gr.Audio(label="Output Combined Audio")
+                        if args.files:
+                            with gr.Column():
+                                vc_volume = gr.Slider(
+                                    minimum=0,
+                                    maximum=10,
+                                    label="Vocal volume",
+                                    value=5,
+                                    interactive=True,
+                                    step=1
+                                )
+                                vc_outputCombine = gr.Audio(label="Output Combined Audio")
+                                vc_combine =  gr.Button("Combine",variant="primary")
                 vc_submit.click(vc_fn, [vc_input, vc_transpose, vc_f0method, vc_index_ratio, tts_mode, tts_text, tts_voice], [vc_output1, vc_output2])
                 tts_mode.change(change_to_tts_mode, [tts_mode], [vc_input, tts_text, tts_voice])
                 if args.files:
                     vc_convert.click(cut_vocal_and_inst, vc_youtube, [vc_vocal_preview, vc_inst_preview, vc_audio_preview, vc_input])
-                    vc_combine.click(combine_vocal_and_inst, vc_output2, vc_outputCombine)
+                    vc_combine.click(combine_vocal_and_inst, [vc_output2, vc_volume], vc_outputCombine)
         app.queue(concurrency_count=1, max_size=20, api_open=args.api).launch(share=args.share)

app.py

@@ -139,6 +139,7 @@ if __name__ == '__main__':
         gr.Markdown(
             "# <center> RVC Models\n"
             "## <center> The input audio should be clean and pure voice without background music.\n"
+            "#### <center> Recommended to use the Google Colab version for more feature.\n"
             "![visitor badge](https://visitor-badge.glitch.me/badge?page_id=ArkanDash.Rvc-Models)\n\n"
             "[![image](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1hx6kKvIuv5XNY1Gai2PEuZhpO5z6xpVh?usp=sharing)\n\n"
             "[![Original Repo](https://badgen.net/badge/icon/github?icon=github&label=Original%20Repo)](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI)"