extern/Thorsten-Voice
1
0
Fork 1
mirror of https://github.com/thorstenMueller/Thorsten-Voice.git synced 2024-11-22 07:53:21 +01:00
Code Issues Packages Projects Releases Wiki Activity

Update on emotional dataset info

Browse Source
This commit is contained in:
Thorsten Mueller 2021-04-11 11:42:24 +02:00
parent 12c6d26dbd
commit 28d81a0fb2
1 changed files with 10 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
README.md
View File

@ -11,8 +11,7 @@
- [Download information](#neutral-dataset-download-information) - [Download information](#neutral-dataset-download-information)
- [Voice "Thorsten" (emotional)](#dataset-Thorsten-emotional) - [Voice "Thorsten" (emotional)](#dataset-Thorsten-emotional)
- [Samples of my emotional voice](#samples-of-my-emotional-voice) - [Emotional dataset information and samples :microphone:](#emotional-dataset-information-and-samples-microphone)
- [Emotional dataset information :microphone:](#emotional-dataset-information-microphone)
- [Emotional dataset download information](#emotional-dataset-download-information) - [Emotional dataset download information](#emotional-dataset-download-information)
- [Pretrained TTS models](#pretrained-tts-models) - [Pretrained TTS models](#pretrained-tts-models)
@ -115,16 +114,7 @@ If you wanna use just a dataset subset (phase1 and/or phase2 and/or phase3) you
## Dataset "Thorsten" emotional ## Dataset "Thorsten" emotional
### Samples of my emotional voice ### Emotional dataset information and samples :microphone:
*Btw. i mentioned, that i'm no professional voice talent, did i?*
> "Mist, wieder nichts geschafft."
*
* [disgusted](./samples/emotional_recording/disgusted.wav)
* [angry](./samples/emotional_recording/angry.wav)
* [amused](./samples/emotional_recording/amused.wav)
* [surprised](./samples/emotional_recording/surprised.wav)
* [sleepy](./samples/emotional_recording/sleepy.wav)
### Emotional dataset information :microphone:
* 300 sentences * 6 emotions = 1.800 recordings * 300 sentences * 6 emotions = 1.800 recordings
* recorded by Thorsten Müller (optimized by Dominik Kreutz) * recorded by Thorsten Müller (optimized by Dominik Kreutz)
* mono * mono
@ -133,14 +123,17 @@ If you wanna use just a dataset subset (phase1 and/or phase2 and/or phase3) you
* no silence at beginning/ending * no silence at beginning/ending
* sentence length: 59 - 148 chars * sentence length: 59 - 148 chars
*Btw. i mentioned, that i'm no professional voice talent, did i?*
> "Mist, wieder nichts geschafft."
| Emotion | Minutes | Sample | | Emotion | Minutes | Sample |
|-----------|---------| --------- | |-----------|---------| --------- |
| Neutral :slightly_smiling_face: | 19 min. | [neutral sample](./samples/emotional_recording/neutral.wav) | | Neutral :slightly_smiling_face: | 19 min. | [neutral sample](./samples/emotional_recording/neutral.wav) |
| Disgusted :nauseated_face: | 23 min. | | | Disgusted :nauseated_face: | 23 min. | [disgusted sample](./samples/emotional_recording/disgusted.wav) |
| Angry :angry: | 20 min. | | | Angry :angry: | 20 min. | [angry sample](./samples/emotional_recording/angry.wav) |
| Amused :grinning: | 18 min. | | | Amused :grinning: | 18 min. | [amused sample](./samples/emotional_recording/amused.wav) |
| Surprised :astonished: | 18 min. | | | Surprised :astonished: | 18 min. | [surprised sample](./samples/emotional_recording/surprised.wav) |
| Sleepy :pensive: | 30 min. | | | Sleepy :pensive: | 30 min. | [sleepy sample](./samples/emotional_recording/sleepy.wav) |
### Emotional dataset download information ### Emotional dataset download information
> Download size: 300MB > Download size: 300MB