Comments (7)
Would you like to contribute?
An alternative is to split a sentence into smaller ones if the number of tokens is greater than some threshold, say, 10.
from sherpa-onnx.
Please see
sherpa-onnx/sherpa-onnx/csrc/offline-tts-vits-impl.h
Lines 178 to 179 in 9ee2943
If token_ids[i].tokens.size()
is larger than a threshold, then you need to split token_ids[i].tokens
into smaller pieces so that each piece's length is smaller than the given threshold.
The basic knowledge is knowing how to split a std::vector<int32_t>
into smaller vectors.
from sherpa-onnx.
I think this should be carefully considered. When the VITS model synthesizes sounds, the pronunciation of a word is related to its context. Improper segmentation may lead to low synthesis effects.
from sherpa-onnx.
By the way, we can limit the changes only to Persian.
from sherpa-onnx.
Yes I want,where should start?
Yes your porpuse is fast and simple.
I will work on it.
from sherpa-onnx.
Please see
sherpa-onnx/sherpa-onnx/csrc/offline-tts-vits-impl.h
Lines 178 to 179 in 9ee2943
If
token_ids[i].tokens.size()
is larger than a threshold, then you need to splittoken_ids[i].tokens
into smaller pieces so that each piece's length is smaller than the given threshold.The basic knowledge is knowing how to split a
std::vector<int32_t>
into smaller vectors.
Ops cpp ?!! :D
Owkey I will get a try
@GeminiT369 it is very important for someone who uses screen readers.
It will be optional that you use or not use this thing also in languages like persian we want to just have a alternative to e-speak and it doesn't matter if it have very small synthesis effects.
But for for someone with visually problem it's important to have a fast tts.
I think maybe if we can reduce models to 2mb it will fix all problems...but we cant do it.
Or I dont know? Maybe we can?
from sherpa-onnx.
from sherpa-onnx.
Related Issues (20)
- [Help wanted] Add various language bindings for online punctuation models
- Call KWS and ASR HOT 5
- Python library deletions HOT 3
- kws 长时间不唤醒之后的第一次唤醒不响应,需要第二次才会唤醒成功,请看看是什么问题呢? 中英文都有同样问题。有没有参数可以设置 HOT 1
- attention_dims does not exist in the metadata HOT 1
- 关键词识别模型加载时间需要30秒!如何优化 ? Keyword spotter model loading time takes 30 seconds! How to optimize? HOT 1
- Whisper recognizer creation is very slow HOT 2
- Whisper medium error with DirectML
- Is org.k2fsa.sherpa.onnx v1.10.17 supporting Android Xamarin? HOT 1
- Add Olive whisper
- Publish on accrescent HOT 3
- wasm kws 报错 HOT 24
- is it possible to have realtime keyword spotting in flutter HOT 5
- How can I use japanese as the language for keyword spotting HOT 2
- build-android-armv7-eabi.sh "Optimization level must be between 0 and 3" HOT 2
- offline model ,how do I configure the device id? HOT 1
- [Feature Request] Add support to onnxruntime-wasm-simd-threaded for better performance in TTS HOT 1
- [BUG] The herpa-onnx-wasm-main-asr.js has serious errors HOT 1
- Running TTS Engine On Node.js Without Saving Files On Server, Auto Delete Temp File Once IT Generated HOT 3
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 sherpa-onnx.