handle whatever zip model structure given in input

src/main.py

@@ -90,12 +90,20 @@ def raise_exception(error_msg, is_webui):
 def get_rvc_model(voice_model, is_webui):
     rvc_model_filename, rvc_index_filename = None, None
     model_dir = os.path.join(rvc_models_dir, voice_model)
-    for file in os.listdir(model_dir):
-        ext = os.path.splitext(file)[1]
-        if ext == '.pth':
-            rvc_model_filename = file
-        if ext == '.index':
-            rvc_index_filename = file
+    #for file in os.listdir(model_dir):
+    #    ext = os.path.splitext(file)[1]
+    #    if ext == '.pth':
+    #        rvc_model_filename = file
+    #    if ext == '.index':
+    #        rvc_index_filename = file
+
+    for root, dirs, files in os.walk(model_dir):
+        # Iterate over the files in the current directory
+        for file in files:
+            # Check if the file has a .pth extension
+            if file.endswith('.pth'):
+                # Append the full path of the file to the list
+                rvc_model_filename = os.path.join(root, file)
 
     if rvc_model_filename is None:
         error_msg = f'No model file exists in {model_dir}.'
@@ -259,7 +267,7 @@ def combine_audio(audio_paths, output_path, main_gain, backup_gain, inst_gain, o
 
 # song_input is the main vocals that is going through the rvc processs
 # backup vocals are the backup vocals to be added at the end
-def song_cover_pipeline(main_vocals, backup_vocals, voice_model, pitch_change, keep_files,
+def song_cover_pipeline(main_vocals, backup_vocals, voice_model, pitch_change,
                         is_webui=0, main_gain=0, backup_gain=0, inst_gain=0, index_rate=0.5, filter_radius=3,
                         rms_mix_rate=1, f0_method='rmvpe', crepe_hop_length=128, protect=0.33, pitch_change_all=0,
                         reverb_rm_size=0.15, reverb_wet=0.2, reverb_dry=0.8, reverb_damping=0.7, output_format='mp3',
@@ -293,8 +301,8 @@ def song_cover_pipeline(main_vocals, backup_vocals, voice_model, pitch_change, k
             os.makedirs(song_dir)
             
         pitch_change = pitch_change * 12 + pitch_change_all
-        ai_vocals_path = os.path.join(song_dir, f'{os.path.basename(os.path.splitext(main_vocals)[0])}_{voice_model}_p{pitch_change}_i{index_rate}_fr{filter_radius}_rms{rms_mix_rate}_pro{protect}_{f0_method}{"" if f0_method != "mangio-crepe" else f"_{crepe_hop_length}"}.wav')
-        ai_cover_path = os.path.join(song_dir, f'{os.path.basename(os.path.splitext(main_vocals)[0])}({voice_model} Ver)_cover.{output_format}')
+        ai_vocals_path = os.path.join(song_dir, f'{os.path.basename(os.path.splitext(main_vocals)[0])}_{os.path.basename(voice_model)}_p{pitch_change}_i{index_rate}_fr{filter_radius}_rms{rms_mix_rate}_pro{protect}_{f0_method}{"" if f0_method != "mangio-crepe" else f"_{crepe_hop_length}"}.wav')
+        ai_cover_path = os.path.join(song_dir, f'{os.path.basename(os.path.splitext(main_vocals)[0])}({os.path.basename(voice_model)} Ver)_cover.{output_format}')
 
         print(f"DEBUG PRINT: ai_vocals_path: {ai_vocals_path}, ai_cover_path: {ai_cover_path}")
 
@@ -330,13 +338,14 @@ def song_cover_pipeline(main_vocals, backup_vocals, voice_model, pitch_change, k
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser(description='Generate a AI cover song in the song_output/id directory.', add_help=True)
-    parser.add_argument('-i', '--song-input', type=str, required=True, help='Link to a YouTube video or the filepath to a local mp3/wav file to create an AI cover of')
-    parser.add_argument('-dir', '--rvc-dirname', type=str, required=True, help='Name of the folder in the rvc_models directory containing the RVC model file and optional index file to use')
-    parser.add_argument('-p', '--pitch-change', type=int, required=True, help='Change the pitch of AI Vocals only. Generally, use 1 for male to female and -1 for vice-versa. (Octaves)')
-    parser.add_argument('-k', '--keep-files', action=argparse.BooleanOptionalAction, help='Whether to keep all intermediate audio files generated in the song_output/id directory, e.g. Isolated Vocals/Instrumentals')
+    parser.add_argument('-main_v', '--main-v', type=str, default= "spongebob.wav", required=False, help='Link to a YouTube video or the filepath to a local mp3/wav file to create an AI cover of')
+    parser.add_argument('-backup_v', '--backup-v', type=str, default="", required=False,
+                        help='Link to a YouTube video or the filepath to a local mp3/wav file to create an AI cover of')
+    parser.add_argument('-dir', '--rvc-dirname', type=str, default = "plankton", required=False, help='Name of the folder in the rvc_models directory containing the RVC model file and optional index file to use')
+    parser.add_argument('-p', '--pitch-change', type=int, required=False, default=0, help='Change the pitch of AI Vocals only. Generally, use 1 for male to female and -1 for vice-versa. (Octaves)')
     parser.add_argument('-ir', '--index-rate', type=float, default=0.5, help='A decimal number e.g. 0.5, used to reduce/resolve the timbre leakage problem. If set to 1, more biased towards the timbre quality of the training dataset')
     parser.add_argument('-fr', '--filter-radius', type=int, default=3, help='A number between 0 and 7. If >=3: apply median filtering to the harvested pitch results. The value represents the filter radius and can reduce breathiness.')
-    parser.add_argument('-rms', '--rms-mix-rate', type=float, default=0.25, help="A decimal number e.g. 0.25. Control how much to use the original vocal's loudness (0) or a fixed loudness (1).")
+    parser.add_argument('-rms', '--rms-mix-rate', type=float, default=0, help="A decimal number e.g. 0.25. Control how much to use the original vocal's loudness (0) or a fixed loudness (1).")
     parser.add_argument('-palgo', '--pitch-detection-algo', type=str, default='rmvpe', help='Best option is rmvpe (clarity in vocals), then mangio-crepe (smoother vocals).')
     parser.add_argument('-hop', '--crepe-hop-length', type=int, default=128, help='If pitch detection algo is mangio-crepe, controls how often it checks for pitch changes in milliseconds. The higher the value, the faster the conversion and less risk of voice cracks, but there is less pitch accuracy. Recommended: 128.')
     parser.add_argument('-pro', '--protect', type=float, default=0.33, help='A decimal number e.g. 0.33. Protect voiceless consonants and breath sounds to prevent artifacts such as tearing in electronic music. Set to 0.5 to disable. Decrease the value to increase protection, but it may reduce indexing accuracy.')
@@ -355,7 +364,7 @@ if __name__ == '__main__':
     if not os.path.exists(os.path.join(rvc_models_dir, rvc_dirname)):
         raise Exception(f'The folder {os.path.join(rvc_models_dir, rvc_dirname)} does not exist.')
 
-    cover_path = song_cover_pipeline(args.song_input, rvc_dirname, args.pitch_change, args.keep_files,
+    cover_path = song_cover_pipeline(main_vocals = "spongebob.wav", backup_vocals=args.backup_v, voice_model = "plankton", pitch_change = args.pitch_change,
                                      main_gain=args.main_vol, backup_gain=args.backup_vol, inst_gain=args.inst_vol,
                                      index_rate=args.index_rate, filter_radius=args.filter_radius,
                                      rms_mix_rate=args.rms_mix_rate, f0_method=args.pitch_detection_algo,