Updating speaker labels

prepare_model.py

@@ -2,39 +2,23 @@ import json
 import os
 import subprocess
 
-def generate_html_output(data, repository_path):
-    with open('speakers.md', 'a') as file:
-        for speaker_id, speaker_info in data.items():
-            out_path = f"{repository_path}/samples/{speaker_id}.wav"
-            age = speaker_info['age']
-            gender = speaker_info['gender']
-            if gender == 'F':
-                gender = 'female'
-            elif gender == "M":
-                gender = 'male'
-            accents = speaker_info['accents']
-            region = speaker_info['region']
-
-            file.write(f"<p>VCTK_{speaker_id}: {age} year old {gender}, {accents} accent ({region})<audio controls><source src=\"{out_path}\" type=\"audio/wav\"></audio> </p>\n")
-
-
 # Load the data from the provided dictionary
 data = {
-    "p226": {"age": 22, "gender": "M", "accents": "English", "region": "Surrey"},
-    "p227": {"age": 38, "gender": "M", "accents": "English", "region": "Cumbria"},
-    "p232": {"age": 23, "gender": "M", "accents": "English", "region": "Southern England"},
-    "p243": {"age": 22, "gender": "M", "accents": "English", "region": "London"},
-    "p254": {"age": 21, "gender": "M", "accents": "English", "region": "Surrey"},
-    "p256": {"age": 24, "gender": "M", "accents": "English", "region": "Birmingham"},
-    "p258": {"age": 22, "gender": "M", "accents": "English", "region": "Southern England"},
-    "p259": {"age": 23, "gender": "M", "accents": "English", "region": "Nottingham"},
-    "p270": {"age": 21, "gender": "M", "accents": "English", "region": "Yorkshire"},
-    "p273": {"age": 23, "gender": "M", "accents": "English", "region": "Suffolk"},
-    "p274": {"age": 22, "gender": "M", "accents": "English", "region": "Essex"},
-    "p278": {"age": 22, "gender": "M", "accents": "English", "region": "Cheshire"},
-    "p279": {"age": 23, "gender": "M", "accents": "English", "region": "Leicester"},
-    "p286": {"age": 23, "gender": "M", "accents": "English", "region": "Newcastle"},
-    "p287": {"age": 23, "gender": "M", "accents": "English", "region": "York"}
+    "VCTK_p226": {"age": 22, "gender": "M", "accents": "English", "region": "Surrey"},
+    "VCTK_p227": {"age": 38, "gender": "M", "accents": "English", "region": "Cumbria"},
+    "VCTK_p232": {"age": 23, "gender": "M", "accents": "English", "region": "Southern England"},
+    "VCTK_p243": {"age": 22, "gender": "M", "accents": "English", "region": "London"},
+    "VCTK_p254": {"age": 21, "gender": "M", "accents": "English", "region": "Surrey"},
+    "VCTK_p256": {"age": 24, "gender": "M", "accents": "English", "region": "Birmingham"},
+    "VCTK_p258": {"age": 22, "gender": "M", "accents": "English", "region": "Southern England"},
+    "VCTK_p259": {"age": 23, "gender": "M", "accents": "English", "region": "Nottingham"},
+    "VCTK_p270": {"age": 21, "gender": "M", "accents": "English", "region": "Yorkshire"},
+    "VCTK_p273": {"age": 23, "gender": "M", "accents": "English", "region": "Suffolk"},
+    "VCTK_p274": {"age": 22, "gender": "M", "accents": "English", "region": "Essex"},
+    "VCTK_p278": {"age": 22, "gender": "M", "accents": "English", "region": "Cheshire"},
+    "VCTK_p279": {"age": 23, "gender": "M", "accents": "English", "region": "Leicester"},
+    "VCTK_p286": {"age": 23, "gender": "M", "accents": "English", "region": "Newcastle"},
+    "VCTK_p287": {"age": 23, "gender": "M", "accents": "English", "region": "York"}
 }
 
 
@@ -56,29 +40,26 @@ speaker_indices = eval(output)
 with open('speakers-log.json', 'r') as file:
     speaker_ids = json.load(file)
 
-# Create the speakers.md file
-with open('speakers.md', 'w') as file:
-    for speaker_idx in speaker_indices:
-        # Remove the 'VCTK_' prefix
-        speaker_id = speaker_idx.replace('VCTK_', '')
 
-        # Lookup the speaker ID in the loaded speaker IDs
-        if speaker_id in speaker_ids:
-            speaker_id_json = speaker_ids[speaker_id]
-        else:
-            continue
+for speaker_idx in speaker_indices:
+    # # Remove the 'VCTK_' prefix
+    speaker_id = speaker_idx
+    # speaker_id = speaker_idx.replace('VCTK_', '')
 
-        # # Generate the TTS command to create the audio file
-        text = f"Hello, I am from {speaker_id_json['region']}. I hope that you will select my voice for your project. Thank you."
-        # # make samples directory if it doesn't exist
-        if not os.path.exists("samples"):
-            os.makedirs("samples")
+    # Lookup the speaker ID in the loaded speaker IDs
+    if speaker_id in speaker_ids:
+        speaker_id_json = speaker_ids[speaker_id]
+    else:
+        continue
 
-        out_path = f"samples/{speaker_id}.wav"
-        tts_command = f"tts --text \"{text}\" --model_path checkpoint_85000.pth --language_idx en --config_path config.json --speaker_idx \"VCTK_{speaker_id}\" --out_path {out_path}"
+    # # Generate the TTS command to create the audio file
+    # text = f"Hello, I am from {speaker_id_json['region']}. I hope that you will select my voice for your project. Thank you."
+    # # make samples directory if it doesn't exist
+    # if not os.path.exists("samples"):
+    #     os.makedirs("samples")
 
-        # Execute the TTS command
-        os.system(tts_command)
+    # out_path = f"samples/{speaker_id}.wav"
+    # tts_command = f"tts --text \"{text}\" --model_path checkpoint_85000.pth --language_idx en --config_path config.json --speaker_idx \"VCTK_{speaker_id}\" --out_path {out_path}"
 
-        # Write the speaker information to the speakers.md file
-        generate_html_output({speaker_id: speaker_id_json}, "https://huggingface.co/voices/VCTK_European_English_Males/resolve/main")
+    # Execute the TTS command
+    # os.system(tts_command)

speakers-log.json

@@ -1,89 +1,89 @@
 {
-  "p226": {
+  "VCTK_p226": {
     "age": 22,
     "gender": "M",
     "accents": "English",
     "region": "Surrey"
   },
-  "p227": {
+  "VCTK_p227": {
     "age": 38,
     "gender": "M",
     "accents": "English",
     "region": "Cumbria"
   },
-  "p232": {
+  "VCTK_p232": {
     "age": 23,
     "gender": "M",
     "accents": "English",
     "region": "Southern England"
   },
-  "p243": {
+  "VCTK_p243": {
     "age": 22,
     "gender": "M",
     "accents": "English",
     "region": "London"
   },
-  "p254": {
+  "VCTK_p254": {
     "age": 21,
     "gender": "M",
     "accents": "English",
     "region": "Surrey"
   },
-  "p256": {
+  "VCTK_p256": {
     "age": 24,
     "gender": "M",
     "accents": "English",
     "region": "Birmingham"
   },
-  "p258": {
+  "VCTK_p258": {
     "age": 22,
     "gender": "M",
     "accents": "English",
     "region": "Southern England"
   },
-  "p259": {
+  "VCTK_p259": {
     "age": 23,
     "gender": "M",
     "accents": "English",
     "region": "Nottingham"
   },
-  "p270": {
+  "VCTK_p270": {
     "age": 21,
     "gender": "M",
     "accents": "English",
     "region": "Yorkshire"
   },
-  "p273": {
+  "VCTK_p273": {
     "age": 23,
     "gender": "M",
     "accents": "English",
     "region": "Suffolk"
   },
-  "p274": {
+  "VCTK_p274": {
     "age": 22,
     "gender": "M",
     "accents": "English",
     "region": "Essex"
   },
-  "p278": {
+  "VCTK_p278": {
     "age": 22,
     "gender": "M",
     "accents": "English",
     "region": "Cheshire"
   },
-  "p279": {
+  "VCTK_p279": {
     "age": 23,
     "gender": "M",
     "accents": "English",
     "region": "Leicester"
   },
-  "p286": {
+  "VCTK_p286": {
     "age": 23,
     "gender": "M",
     "accents": "English",
     "region": "Newcastle"
   },
-  "p287": {
+  "VCTK_p287": {
     "age": 23,
     "gender": "M",
     "accents": "English",