Hugging Face's logo

voices
/
VCTK_British_English_Females

Text-to-Speech
Transformers
English
tts
audio
text to speech
coqui
coqui-tts
Inference Endpoints
Model card Files Community
jvision commited on
Commit
6585abb
•
1 Parent(s): 7d8a3f7

normalizing entries

Browse files
Files changed (3) hide show
  1. prepare_model.py +86 -0
  2. vctk_speakers.json → speakers-log.json +0 -0
  3. speakers.md +18 -24
prepare_model.py ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import json
2
+ import os
3
+ import subprocess
4
+
5
+ def generate_html_output(data, repository_path):
6
+ with open('speakers.md', 'a') as file:
7
+ for speaker_id, speaker_info in data.items():
8
+ out_path = f"{repository_path}/samples/{speaker_id}.wav"
9
+ age = speaker_info['age']
10
+ gender = speaker_info['gender']
11
+ if gender == 'F':
12
+ gender = 'female'
13
+ elif gender == "M":
14
+ gender = 'male'
15
+ accents = speaker_info['accents']
16
+ region = speaker_info['region']
17
+
18
+ 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")
19
+
20
+
21
+ # Load the data from the provided dictionary
22
+ data = {
23
+ "p225": {"age": 23, "gender": "F", "accents": "English", "region": "Southern England", "comments": ""},
24
+ "p228": {"age": 22, "gender": "F", "accents": "English", "region": "Southern England", "comments": ""},
25
+ "p229": {"age": 23, "gender": "F", "accents": "English", "region": "Southern England", "comments": ""},
26
+ "p230": {"age": 22, "gender": "F", "accents": "English", "region": "Stockton-on-tees", "comments": ""},
27
+ "p231": {"age": 23, "gender": "F", "accents": "English", "region": "Southern England", "comments": ""},
28
+ "p233": {"age": 23, "gender": "F", "accents": "English", "region": "Staffordshire", "comments": ""},
29
+ "p236": {"age": 23, "gender": "F", "accents": "English", "region": "Manchester", "comments": ""},
30
+ "p239": {"age": 22, "gender": "F", "accents": "English", "region": "Southwest England", "comments": ""},
31
+ "p240": {"age": 21, "gender": "F", "accents": "English", "region": "Southern England", "comments": ""},
32
+ "p244": {"age": 22, "gender": "F", "accents": "English", "region": "Manchester", "comments": ""},
33
+ "p250": {"age": 22, "gender": "F", "accents": "English", "region": "Southeast England", "comments": ""},
34
+ "p257": {"age": 24, "gender": "F", "accents": "English", "region": "Southern England", "comments": ""},
35
+ "p267": {"age": 23, "gender": "F", "accents": "English", "region": "Yorkshire", "comments": ""},
36
+ "p268": {"age": 23, "gender": "F", "accents": "English", "region": "Southern England", "comments": ""},
37
+ "p269": {"age": 20, "gender": "F", "accents": "English", "region": "Newcastle", "comments": ""},
38
+ "p276": {"age": 24, "gender": "F", "accents": "English", "region": "Oxford", "comments": ""},
39
+ "p277": {"age": 23, "gender": "F", "accents": "English", "region": "Northeast England", "comments": ""},
40
+ "p282": {"age": 23, "gender": "F", "accents": "English", "region": "Newcastle", "comments": ""}
41
+ }
42
+
43
+ # Convert the data to JSON format
44
+ json_data = json.dumps(data, indent=2)
45
+
46
+ # Save the JSON data to a file
47
+ with open('speakers-log.json', 'w') as file:
48
+ file.write(json_data)
49
+
50
+ # Run the TTS command to get the speaker indices
51
+ command = "tts --model_path checkpoint_85000.pth --config_path config.json --list_speaker_idxs | grep -vE '^(\s*\||\s*>|\s*$)'"
52
+ output = subprocess.check_output(command, shell=True, text=True)
53
+
54
+ # Parse the JSON output into a Python dictionary
55
+ speaker_indices = eval(output)
56
+
57
+ # Load the speaker IDs from speakers.json
58
+ with open('speakers-log.json', 'r') as file:
59
+ speaker_ids = json.load(file)
60
+
61
+ # Create the speakers.md file
62
+ with open('speakers.md', 'w') as file:
63
+ for speaker_idx in speaker_indices:
64
+ # Remove the 'VCTK_' prefix
65
+ speaker_id = speaker_idx.replace('VCTK_', '')
66
+
67
+ # Lookup the speaker ID in the loaded speaker IDs
68
+ if speaker_id in speaker_ids:
69
+ speaker_id_json = speaker_ids[speaker_id]
70
+ else:
71
+ continue
72
+
73
+ # # Generate the TTS command to create the audio file
74
+ # text = f"Hello, I am from {speaker_id_json['region']}. I hope that you will select my voice for your project. Thank you."
75
+ # # make samples directory if it doesn't exist
76
+ # if not os.path.exists("samples"):
77
+ # os.makedirs("samples")
78
+
79
+ out_path = f"samples/{speaker_id}.wav"
80
+ 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}"
81
+
82
+ Execute the TTS command
83
+ os.system(tts_command)
84
+
85
+ # Write the speaker information to the speakers.md file
86
+ generate_html_output({speaker_id: speaker_id_json}, "https://huggingface.co/voices/VCTK_European_English_Females/resolve/main")
vctk_speakers.json → speakers-log.json RENAMED
File without changes
speakers.md CHANGED
@@ -1,24 +1,18 @@
1
- <audio controls>
2
- <source src="horse.ogg" type="audio/ogg">
3
- <source src="horse.mp3" type="audio/mpeg">
4
- Your browser does not support the audio element.
5
- </audio>
6
-
7
- [p225](samples/p225.wav) Age 23 Gender F Accents English Region Southern England Comments
8
- [p228](samples/p228.wav) Age 22 Gender F Accents English Region Southern England Comments
9
- [p229](samples/p229.wav) Age 23 Gender F Accents English Region Southern England Comments
10
- [p230](samples/p230.wav) Age 22 Gender F Accents English Region Stockton-on-tees Comments
11
- [p231](samples/p231.wav) Age 23 Gender F Accents English Region Southern England Comments
12
- [p233](samples/p233.wav) Age 23 Gender F Accents English Region Staffordshire Comments
13
- [p236](samples/p236.wav) Age 23 Gender F Accents English Region Manchester Comments
14
- [p239](samples/p239.wav) Age 22 Gender F Accents English Region Southwest England Comments
15
- [p240](samples/p240.wav) Age 21 Gender F Accents English Region Southern England Comments
16
- [p244](samples/p244.wav) Age 22 Gender F Accents English Region Manchester Comments
17
- [p250](samples/p250.wav) Age 22 Gender F Accents English Region Southeast England Comments
18
- [p257](samples/p257.wav) Age 24 Gender F Accents English Region Southern England Comments
19
- [p267](samples/p267.wav) Age 23 Gender F Accents English Region Yorkshire Comments
20
- [p268](samples/p268.wav) Age 23 Gender F Accents English Region Southern England Comments
21
- [p269](samples/p269.wav) Age 20 Gender F Accents English Region Newcastle Comments
22
- [p276](samples/p276.wav) Age 24 Gender F Accents English Region Oxford Comments
23
- [p277](samples/p277.wav) Age 23 Gender F Accents English Region Northeast England Comments
24
- [p282](samples/p282.wav) Age 23 Gender F Accents English Region Newcastle Comments
 
1
+ <p>VCTK_p225: 23 year old female, English accent (Southern England)<audio controls><source src="https://huggingface.co/voices/VCTK_European_English_Females/resolve/main/samples/p225.wav" type="audio/wav"></audio> </p>
2
+ <p>VCTK_p228: 22 year old female, English accent (Southern England)<audio controls><source src="https://huggingface.co/voices/VCTK_European_English_Females/resolve/main/samples/p228.wav" type="audio/wav"></audio> </p>
3
+ <p>VCTK_p229: 23 year old female, English accent (Southern England)<audio controls><source src="https://huggingface.co/voices/VCTK_European_English_Females/resolve/main/samples/p229.wav" type="audio/wav"></audio> </p>
4
+ <p>VCTK_p230: 22 year old female, English accent (Stockton-on-tees)<audio controls><source src="https://huggingface.co/voices/VCTK_European_English_Females/resolve/main/samples/p230.wav" type="audio/wav"></audio> </p>
5
+ <p>VCTK_p231: 23 year old female, English accent (Southern England)<audio controls><source src="https://huggingface.co/voices/VCTK_European_English_Females/resolve/main/samples/p231.wav" type="audio/wav"></audio> </p>
6
+ <p>VCTK_p233: 23 year old female, English accent (Staffordshire)<audio controls><source src="https://huggingface.co/voices/VCTK_European_English_Females/resolve/main/samples/p233.wav" type="audio/wav"></audio> </p>
7
+ <p>VCTK_p236: 23 year old female, English accent (Manchester)<audio controls><source src="https://huggingface.co/voices/VCTK_European_English_Females/resolve/main/samples/p236.wav" type="audio/wav"></audio> </p>
8
+ <p>VCTK_p239: 22 year old female, English accent (Southwest England)<audio controls><source src="https://huggingface.co/voices/VCTK_European_English_Females/resolve/main/samples/p239.wav" type="audio/wav"></audio> </p>
9
+ <p>VCTK_p240: 21 year old female, English accent (Southern England)<audio controls><source src="https://huggingface.co/voices/VCTK_European_English_Females/resolve/main/samples/p240.wav" type="audio/wav"></audio> </p>
10
+ <p>VCTK_p244: 22 year old female, English accent (Manchester)<audio controls><source src="https://huggingface.co/voices/VCTK_European_English_Females/resolve/main/samples/p244.wav" type="audio/wav"></audio> </p>
11
+ <p>VCTK_p250: 22 year old female, English accent (Southeast England)<audio controls><source src="https://huggingface.co/voices/VCTK_European_English_Females/resolve/main/samples/p250.wav" type="audio/wav"></audio> </p>
12
+ <p>VCTK_p257: 24 year old female, English accent (Southern England)<audio controls><source src="https://huggingface.co/voices/VCTK_European_English_Females/resolve/main/samples/p257.wav" type="audio/wav"></audio> </p>
13
+ <p>VCTK_p267: 23 year old female, English accent (Yorkshire)<audio controls><source src="https://huggingface.co/voices/VCTK_European_English_Females/resolve/main/samples/p267.wav" type="audio/wav"></audio> </p>
14
+ <p>VCTK_p268: 23 year old female, English accent (Southern England)<audio controls><source src="https://huggingface.co/voices/VCTK_European_English_Females/resolve/main/samples/p268.wav" type="audio/wav"></audio> </p>
15
+ <p>VCTK_p269: 20 year old female, English accent (Newcastle)<audio controls><source src="https://huggingface.co/voices/VCTK_European_English_Females/resolve/main/samples/p269.wav" type="audio/wav"></audio> </p>
16
+ <p>VCTK_p276: 24 year old female, English accent (Oxford)<audio controls><source src="https://huggingface.co/voices/VCTK_European_English_Females/resolve/main/samples/p276.wav" type="audio/wav"></audio> </p>
17
+ <p>VCTK_p277: 23 year old female, English accent (Northeast England)<audio controls><source src="https://huggingface.co/voices/VCTK_European_English_Females/resolve/main/samples/p277.wav" type="audio/wav"></audio> </p>
18
+ <p>VCTK_p282: 23 year old female, English accent (Newcastle)<audio controls><source src="https://huggingface.co/voices/VCTK_European_English_Females/resolve/main/samples/p282.wav" type="audio/wav"></audio> </p>