bigpon / qpnet Goto Github PK
View Code? Open in Web Editor NEWQuasi-Periodic WaveNet Pytorch implementation
Home Page: https://bigpon.github.io/QuasiPeriodicWaveNet_demo/
License: Apache License 2.0
Quasi-Periodic WaveNet Pytorch implementation
Home Page: https://bigpon.github.io/QuasiPeriodicWaveNet_demo/
License: Apache License 2.0
I failed to achieve the results in the paper when I trained the model myself. Can you provide a trained model?
Hello
First of all, thank you for sharing this project.
I would like to evaluate the performance of the vocoder by running one of your pre-trained model. However, after extracting the features of a test file with runFE script, it get an error when trying to read the generated files in qpnet_decode.py
The call to qpnet_decode is as follows :
python ./bin/qpnet_decode.py
--feats /home/Julien/QPNet-master/QPNet-master/h5/33.h5
--stats /home/Julien/QPNet-master/QPNet-master/corpus/VCC2018/stats/list_stats.h5
--config /home/Julien/QPNet-master/QPNet-master/qpnet_models/Avcc18tr_Wvcc18tr_d8/model.conf
--outdir /home/Julien/QPNet-master/QPNet-master/qpnet_output/feat_id.wav
--checkpoint /home/Julien/QPNet-master/QPNet-master/qpnet_models/Avcc18tr_Wvcc18tr_d8//checkpoint-final.pkl
--fs 22050 --batch_size 1 --extra_memory False --seed 100 --n_gpus 2 --f0_factor 1.0 --f0_dim_index 1
As input, I use a 22050Hz wav file (33.wav) and I generated the feats and stats using step 2 and 3 of runFE.py
The complete error message is :
Traceback (most recent call last):
File "./bin/qpnet_decode.py", line 335, in <module>
main()
File "./bin/qpnet_decode.py", line 252, in main
feat_list = read_txt(args.feats)
File "/home/Julien/QPNet-master/QPNet-master/src/utils/utils.py", line 161, in read_txt
filenames = f.readlines()
File "/home/Julien/miniconda3/envs/venvQPNet/lib/python3.6/codecs.py", line 321, in decode
(result, consumed) = self._buffer_decode(data, self.errors, final)
UnicodeDecodeError: 'utf-8' codec can't decode byte 0x89 in position 0: invalid start byte
Could you please help me with this ? I guess I might be doing this the wrong way but I don't know how else I can simply extract the features of a test file and try out a model with it
Thanks again for sharing this and for your time
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.