Comments (2)
Hey @yuan1615, thanks for sharing the benchmark, I wasn't aware of i!
Training from-scratch for this is totally feasible, but 32 code-books seems like a lot, as the model would use 32 embedding layers and 32 LM heads. Additionally, the benchmark doesn't seem to use subjective metrics, so it might be non conclusive!
from parler-tts.
Thank you for the reply, I also feel that using 32 seems a bit excessive.
from parler-tts.
Related Issues (20)
- [Question] "I got strongly recommended to pass the `sampling_rate` argument to this function... " Is this expected? HOT 5
- problem with DataCollatorParlerTTSWithPadding HOT 2
- [Inference] Set do_sample=False disrupt the generation HOT 1
- Fine-Tuning colab error HOT 5
- Custom pronunciation for words - any thoughts / recommendations about how best to handle them? HOT 1
- Flash Attention Support HOT 3
- run_parler_tts_training.py gives datasets.table.CastError error and failure HOT 1
- Provide an OpenAI compatible web-server that can be deployed using Docker HOT 2
- attention_mask HOT 3
- Exception in label generated HOT 3
- LM Output Vocab Size and Extra Tokens HOT 1
- Error: Assertion `srcIndex < srcSelectDimSize` failed HOT 1
- sharing results of korean(+english) bilingual training HOT 12
- How to predict after finetune? There is no config.json in checkpoint dir. HOT 3
- Are there plans to open source the training data? HOT 1
- How do you change the sampling rate while keeping the sound quality roughly the same? HOT 2
- GPU parallel HOT 6
- TypeError: iteration over a 0-d tensor HOT 7
- How to do with flan-t5 when i want to finetune based on Mini v0.1 but not from scratch? Flan t5 can not deal my language.
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 parler-tts.