Merge branch 'bokeh-interactive-1' into dev

speaker_encoder/README.md

@@ -1,8 +1,12 @@
 ### Speaker embedding (Experimental)
 
-This is an implementation of https://arxiv.org/abs/1710.10467. This model can be used for voice and speaker embedding. So you can generate d-vectors for multi-speaker TTS or prune bad samples from your TTS dataset. Below is an example showing embedding results of various speakers. You can generate the same plot with the provided notebook. 
+This is an implementation of https://arxiv.org/abs/1710.10467. This model can be used for voice and speaker embedding.
 
-![](https://user-images.githubusercontent.com/1402048/64603079-7fa5c100-d3c8-11e9-88e7-88a00d0e37d1.png)
+With the code here you can generate d-vectors for both multi-speaker and single-speaker TTS datasets, then visualise and explore them along with the associated audio files in an interactive chart.
+
+Below is an example showing embedding results of various speakers. You can generate the same plot with the provided notebook as demonstrated in [this video](https://youtu.be/KW3oO7JVa7Q). 
+
+![](umap.png)
 
 Download a pretrained model from [Released Models](https://github.com/mozilla/TTS/wiki/Released-Models) page.
 

speaker_encoder/compute_embeddings.py

@@ -14,27 +14,52 @@ parser = argparse.ArgumentParser(
     description="Compute embedding vectors for each wav file in a dataset. "
 )
 parser.add_argument(
-    "model_path", type=str, help="Path to model outputs (checkpoint, tensorboard etc.)."
+    'data_path',
-)
+    type=str,
+    help='Data path for wav files - directory or CSV file')
 parser.add_argument(
     "config_path", type=str, help="Path to config file for training.",
 )
 parser.add_argument(
     "data_path", type=str, help="Defines the data path. It overwrites config.json."
 )
-parser.add_argument("output_path", type=str, help="path for training outputs.")
+parser.add_argument(
-parser.add_argument("--use_cuda", type=bool, help="flag to set cuda.", default=False)
+    '--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)
+data_path = args.data_path
-output_files = [
+split_ext = os.path.splitext(data_path)
-    wav_file.replace(args.data_path, args.output_path).replace(".wav", ".npy")
+sep = args.separator
-    for wav_file in wav_files
+
-]
+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:
     os.makedirs(os.path.dirname(output_file), exist_ok=True)