Add Bokeh interactive plotting

speaker_encoder/compute_embeddings.py

@@ -28,7 +28,7 @@ parser.add_argument(
 parser.add_argument(
     'data_path',
     type=str,
-    help='Defines the data path. It overwrites config.json.')
+    help='Data path for wav files - directory or CSV file')
 parser.add_argument(
     'output_path',
     type=str,
@@ -36,14 +36,42 @@ parser.add_argument(
 parser.add_argument(
     '--use_cuda', type=bool, help='flag to set cuda.', default=False
 )
+parser.add_argument(
+    '--separator', type=str, help='Separator used in file if CSV is passed for data_path', default='|'
+)
 args = parser.parse_args()
 
 
 c = load_config(args.config_path)
 ap = AudioProcessor(**c['audio'])
 
-wav_files = glob.glob(args.data_path + '/**/*.wav', recursive=True)
-output_files = [wav_file.replace(args.data_path, args.output_path).replace(
+data_path = args.data_path
+split_ext = os.path.splitext(data_path)
+sep = args.separator
+
+if len(split_ext) > 0 and split_ext[1].lower() == '.csv':
+    # Parse CSV
+    print(f'CSV file: {data_path}')
+    with open(data_path) as f:
+        wav_path = os.path.join(os.path.dirname(data_path), 'wavs')
+        wav_files = []
+        print(f'Separator is: {sep}')
+        for line in f:
+            components = line.split(sep)
+            if len(components) != 2:
+                print("Invalid line")
+                continue
+            wav_file = os.path.join(wav_path, components[0] + '.wav')
+            #print(f'wav_file: {wav_file}')
+            if os.path.exists(wav_file):
+                wav_files.append(wav_file)
+    print(f'Count of wavs imported: {len(wav_files)}')
+else:
+    # Parse all wav files in data_path
+    wav_path = data_path
+    wav_files = glob.glob(data_path + '/**/*.wav', recursive=True)
+
+output_files = [wav_file.replace(wav_path, args.output_path).replace(
     '.wav', '.npy') for wav_file in wav_files]
 
 for output_file in output_files: