extern/Thorsten-Voice
1
0
Fork 1
mirror of https://github.com/thorstenMueller/Thorsten-Voice.git synced 2024-11-21 23:43:12 +01:00
Code Issues Packages Projects Releases Wiki Activity

Added graphics, google drive download link

Browse Source
This commit is contained in:
Thorsten Müller 2019-11-03 20:50:49 +01:00 committed by GitHub
parent 2a34a4970d
commit e19c006b4d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 9 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
README.md
View File

@ -11,6 +11,7 @@ Ich möchte meinen kleinen bescheidenen Beitrag leisten und stelle meine Stimme
# Klingt gut. Was genau gibt es hier.
* Der Corpus als CSV Format, so dass er vom Mimic-Recording-Studio verwendet werden kann (Datenquelle: Mozilla commion voice (anteilig))
* Die LJSpeech-1.1 Struktur (metadata.csv und zugehörige WAV-Dateien) zur Verarbeitung mit mimic2 (basiert auf Tacotron)
>> Aufgrund von Github-Größenbeschränkung liegen die gezippten WAV-Dateien im Google Drive ([Download-Link](https://drive.google.com/drive/folders/12wihZ6X7OYf4-7GG4b-o-f5RaNNPKsqA?usp=sharing)
# Aktueller Stand
Aufnahmen 3.000 von 20.000 Sätzen mit einer gesprochenen Länge von 5 Stunden, 10 Minuten und einer Sprechgeschwindgkeit von ca. 12-13 Zeichen pro Sekunde.
@ -33,6 +34,7 @@ I want to make my small modest contribution and make my voice available under th
# Sounds good. What exactly is here.
* The Corpus as a CSV format that can be used by the Mimic recording studio (datasource is partial mozilla common voice project)
* The LJSpeech-1.1 structure (metadata.csv and associated WAV files) for processing with mimic2 (based on Tacotron)
>> Due github size restrictions the compressed wav-files can be downloaded from google drive ([Download-Link](https://drive.google.com/drive/folders/12wihZ6X7OYf4-7GG4b-o-f5RaNNPKsqA?usp=sharing)
# Current status
Record 3,000 of 20,000 sentences with a spoken length of 5 hours, 10 minutes and a speech speed of approximately 12-13 characters per second.
@ -43,6 +45,13 @@ If you use my (concrete) TTS voice I would be grateful for an info about the pro
Also, my thanks go to the projects / communities of Mozilla Common Voice and MyCroft / Mimic. Especially to Lindsay Saunders (Mozilla) for nice contact and eltocino, gras64, dominik from the MyCroft community for the patience to patiently answer my beginner questions :-).
# Mimic analyse(.py) results (after 5k spoken phrases)
![char_len_vs_avg_secs](./img/5000_phrases_char_len_vs_avg_secs.png?raw=true "char_len_vs_avg_secs")
![char_len_vs_med_secs](./img/5000_phrases_char_len_vs_med_secs.png?raw=true "char_len_vs_med_secs")
![char_len_vs_mode_secs](./img/5000_phrases_char_len_vs_mode_secs.png?raw=true "char_len_vs_mode_secs")
![char_len_vs_num_samples](./img/5000_phrases_char_len_vs_num_samples.png?raw=true "char_len_vs_num_samples")
![char_len_vs_std](./img/5000_phrases_char_len_vs_std.png?raw=true "char_len_vs_std")
# Links
* https://voice.mozilla.org/
* https://github.com/mozilla/CorporaCreator