Comments (4)
For numerics and acronyms, we can simply preprocess the string before synthesizing using search and replace or regex.
This is no show stopper.
from tts.
I've been thinking about the same. Especially speech rate.
I've also come across some text that isn't read correctly, like number ranges (i.e., 400-750) and acronyms (i.e., MPH). This could be interpreted correctly via mark-up configuration.
from tts.
This level of detail is not possible with coqui TTS yet due to the limits of the open datasets.
Depending on which model you use, it might struggle with the acronyms and numbers too.
These are limitations due to the use of a publicly available dataset. Most commercial systems use specially created TTS datasets.
from tts.
That's true. Some of the models we release use Phonemes and a text front-end to do the work. You might like to try them.
The only model that only use characters is tts_models/en/ljspeech/tacotron2-DDC
the rest is more robust to such variations.
Hopefully we'll update this mode soon to use a more advance front end.
from tts.
Related Issues (20)
- Design improvements in the bash entry point HOT 1
- [Bug] Fine tuned XTTS v2 produces strange sounds for short text HOT 10
- Can't download train dataset and models when fineturn with XTTS_FT.ipynb[Bug] HOT 1
- [Feature request] Does it support Chinese speech synthesis HOT 1
- Value Error : target loss not found[Bug] HOT 4
- [Bug] result audio repeat some word many times at end HOT 1
- Added Thai, Indonesian, Filipino, Malaysian, Burmese, Cambodian, Vietnamese and Tamil language on a XTTS V2 Huggingface space HOT 3
- 1/17 Install Error[Bug] HOT 1
- [Bug] LLVM ERROR: Symbol not found: __svml_cosf8_ha HOT 1
- [Bug] 'dict_keys' object has no attribute 'keys' HOT 3
- [Bug] GlowTTS / Tacotron2 Training stuck and fail HOT 1
- Add "host" argument to the server.py script HOT 2
- [Feature request] Add Libtashkeel for Arabic Diacritization HOT 1
- [Bug] frpc_windows_amd64_v0.2 detected as a virus HOT 1
- [Bug] Slow length computation after commit 5dcc16d HOT 1
- Numpy 1.22.0 and 1.24.3 Problem with TTS 0.22.0 and Librosa 0.10.0 and 0.10.1 HOT 5
- [Bug] Issues and solution used till now to generate deep fake.
- [Bug] Model won't download HOT 2
- [Bug] HifiGAN Generator throwing error HOT 1
- Unable to download TTS models in docker environment HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from tts.