| .github | ||
| docs | ||
| helperScripts | ||
| samples/thorsten-21.06-emotional | ||
| Youtube | ||
| CITATION.cff | ||
| EvolutionOfThorstenDataset.pdf | ||
| german_corpus-mimic_recording_studio.csv | ||
| LICENSE | ||
| Logo_Thorsten-Voice.png | ||
| README.md | ||
| RecordingQuality.csv | ||
| Thorsten-Voice_Logo.svg | ||
Motivation for Thorsten-Voice project 🗣️ 💬
A free to use, offline working, high quality german TTS voice should be available for every project without any license struggling.
Personal words by Thorsten Müller
I contribute my voice as a person believing in a world where all people are equal. No matter of gender, sexual orientation, religion, skin color and geocoordinates of birth location. A global world where everybody is warmly welcome on any place on this planet and open and free knowledge and education is available to everyone. 🌍 (Thorsten Müller)
Please keep in mind, that i am no professional voice talent. I'm just a normal guy sharing his voice with the world.
Social media
Feel free to contact me on social media 🤗.
| Platform | Link |
|---|---|
| Youtube | ThorstenVoice on Youtube |
| Thorsten Müller on LinkedIn | |
| ThorstenVoice on Twitter | |
| Huggingface | ThorstenVoice on Huggingface |
| ThorstenVoice on Instagram |
Voice-Datasets
All my "Thorsten-Voice" datasets are listed and downloadable on Zenodo. Qoutation is highly appreciated in case you use them in your projects, products or papers.
| Dataset | DOI Link |
|---|---|
| Thorsten-Voice Dataset 2021.02 (Neutral) |  |
| Thorsten-Voice Dataset 2021.06 (Emotional) |  |
| Thorsten-Voice Dataset 2022.10 (Neutral) |  |
| Thorsten-Voice Dataset 2023.09 (Hessisch) |  |
Thorsten-Voice Dataset 2021.02 (Neutral)
@dataset{muller_2021_5525342,
author = {Müller, Thorsten and
Kreutz, Dominik},
title = {Thorsten-Voice Dataset 2021.02},
month = sep,
year = 2021,
note = {{Please use it to make the world a better place for
whole humankind.}},
publisher = {Zenodo},
version = {3.0},
doi = {10.5281/zenodo.5525342},
url = {https://doi.org/10.5281/zenodo.5525342}
}
Dataset summary
- Recorded by Thorsten Müller
- Optimized by Dominik Kreutz
- LJSpeech file and directory structure
- 22.668 recorded phrases (wav files)
- More than 23 hours of pure audio
- Samplerate 22.050Hz
- Mono
- Normalized to -24dB
- Phrase length (min/avg/max): 2 / 52 / 180 chars
- No silence at beginning/ending
- Avg spoken chars per second: 14
- Sentences with question mark: 2.780
- Sentences with exclamation mark: 1.840
Dataset evolution
As described in the PDF document (evolution of thorsten dataset) this dataset consists of three recording phases.
- Phase 1: Recorded with a cheap usb microphone (low quality)
- Phase 2: Recorded with a good microphone (good quality)
- Phase 3: Recorded with same good microphone but longer phrases (> 100 chars) (good quality)
If you want to use a dataset subset you can see which files belong to which recording phase in recording quality csv file.
Thorsten-Voice Dataset 2021.06 (Emotional)
@dataset{muller_2021_5525023,
author = {Müller, Thorsten and
Kreutz, Dominik},
title = {Thorsten-Voice Dataset 2021.06 emotional},
month = sep,
year = 2021,
note = {{Please use it to make the world a better place for
whole humankind.}},
publisher = {Zenodo},
version = {2.0},
doi = {10.5281/zenodo.5525023},
url = {https://doi.org/10.5281/zenodo.5525023}
}
All emotional recordings where recorded by myself and i tried to feel and pronounce that emotion even if the phrase context does not match that emotion. Example: I pronounced the sleepy recordings in the tone i have shortly before falling asleep.
Dataset summary
- Recorded by Thorsten Müller
- Optimized by Dominik Kreutz
- 300 sentences * 8 emotions = 2.400 recordings
- Mono
- Samplerate 22.050Hz
- Normalized to -24dB
- No silence at beginning/ending
- Sentence length: 59 - 148 chars
Thorsten-Voice Dataset 2022.10 (Neutral)
🗣️ Listen to some audio recordings from this dataset here.
@dataset{muller_2022_7265581,
author = {Müller, Thorsten and
Kreutz, Dominik},
title = {Thorsten-Voice Dataset 2022.10},
month = nov,
year = 2022,
publisher = {Zenodo},
version = {1.0},
doi = {10.5281/zenodo.7265581},
url = {https://doi.org/10.5281/zenodo.7265581}
}
Thorsten-Voice Dataset 2023.09 (Hessisch)
@dataset{muller_2024_10511260,
author = {Müller, Thorsten and
Kreutz, Dominik},
title = {Thorsten-Voice Dataset 2023.09 Hessisch},
month = jan,
year = 2024,
publisher = {Zenodo},
doi = {10.5281/zenodo.10511260},
url = {https://doi.org/10.5281/zenodo.10511260}
}
TTS Models
Based on these opensource voice datasets several TTS (text to speech) models have been trained using AI / machine learning technology.
Thorsten-22.05-VITS
Trained on dataset Thorsten-22.05-neutral. Audio samples are available on Thorsten-Voice website.
To run TTS server just follow these steps:
- pip install tts==0.7.1
- tts-server --model_name tts_models/de/thorsten/vits
- Open browser on http://localhost:5002 and enjoy playing
Thorsten-22.08-Tacotron2-DDC
Trained on dataset Thorsten-22.05-neutral. Audio samples are available on Thorsten-Voice website.
To run TTS server just follow these steps:
- pip install tts==0.8.0
- tts-server --model_name tts_models/de/thorsten/tacotron2-DDC
- Open browser on http://localhost:5002 and enjoy playing
Silero
You can use a free A-GPL licensed models trained on Thorsten-21.02-neutral dataset via the silero-models project.
ZDisket
ZDisket made a tool called TensorVox for setting up an TTS environment on Windows and included a german TTS model trained by monatis. Thanks for sharing that 👍. See it in action on Youtube.
Support & Thanks
If you like my voice contribution and would like to support my effort for an opensource voice technology future, you can support me, if you like:
- Subscribe to my "https://youtube.com/@ThorstenMueller/" youtube channel and follow me on my social media profiles
- Buy me a tea using Ko-Fi or Github sponsor
I want to say thank you to great people who supported me on this journey with nice words, support and compute power: Thanks El-Tocino, Eren Gölge, Gras64, Kris Gesling, Nmstoker, Othiele, Repodiac, SanjaESC, Synesthesiam.
Special thanks to my dear colleague, Sebastian Kraus, for supporting me with audio recording equipment and for being the creative mastermind behind the logo design and of course to the dear Dominik (@domcross) for him being so close by my side on this amazing journey.
Public talks
I really want to bring the topic "Open Voice For An Open Future" to a bigger public attention.
- I've been part of a Linux User Group podcast about Mycroft AI and talked on my TTS efforts on that in (May 2021).
- I was invited by Yusuf from Turkish tensorflow community to talk on "How to make machines speak with your own voice". This talk has been streamed live on Youtube and is available here. If you're interested on the showed slides, feel free to download my presentation here (June 2021) )
- I've been invited as speaker on VoiceLunch language & linguistics on 03.01.2022. Here are my slides (January 2022).
Youtube channel
In summer 2021 i've started to share my lessons learned and experiences on open voice tech, in special TTS on my little Youtube channel. If you check out and like my videos i'd happy to welcome you as subscriber and member of my little Youtube community.