Comments (4)
Wadaboa
commented on August 27, 2024
Hi there, please have a look at the src/datasets.py file. You'd need to create a new subclass of SpeakerDataset and implement the 3 abstract methods get_speakers_utterances, get_sample and get_path. You can then use your new custom class in place of LibriSpeechDataset and VCTKDataset.
Let me know if you have any other questions. Thanks,
Alessio.
from titanet.
yy835055664
commented on August 27, 2024
I am very glad that you can provide such careful guidance, and I will continue to reproduce your code according to your ideas.
…---Original---
From: "Alessio ***@***.***>
Date: Sun, May 1, 2022 18:33 PM
To: ***@***.***>;
Cc: ***@***.******@***.***>;
Subject: Re: [Wadaboa/titanet] data set (Issue #3)
Hi there, please have a look at the src/datasets.py file. You'd need to create a new subclass of SpeakerDataset and implement the 3 abstract methods get_speakers_utterances, get_sample and get_path. You can then use your new custom class in place of LibriSpeechDataset and VCTKDataset.
Let me know if you have any other questions. Thanks,
Alessio.
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: ***@***.***>
from titanet.
yy835055664
commented on August 27, 2024
Hi, thank you so much for sharing this code.
Recently, I have been reproducing and learning your project. Regarding custom data sets, both data sets in your project use torchaudio's own data. I have tried custom data in the past few days, but there have been many problems, resulting in failure. Hope you can guide me on non-torchaudio data such as the voxceleb dataset. thank you very much!
…------------------ 原始邮件 ------------------
发件人: "Wadaboa/titanet" ***@***.***>;
发送时间: 2022年5月1日(星期天) 晚上6:33
***@***.***>;
***@***.******@***.***>;
主题: Re: [Wadaboa/titanet] data set (Issue #3)
Hi there, please have a look at the src/datasets.py file. You'd need to create a new subclass of SpeakerDataset and implement the 3 abstract methods get_speakers_utterances, get_sample and get_path. You can then use your new custom class in place of LibriSpeechDataset and VCTKDataset.
Let me know if you have any other questions. Thanks,
Alessio.
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: ***@***.***>
from titanet.
Wadaboa
commented on August 27, 2024
Hi there,
I just pushed a commit to the repo that contains an implementation of VoxCeleb1 and VoxCeleb2. The first version of VoxCeleb is included in the latest release of torchaudio (0.13.0), hence it was straightforward to implement. Instead, VoxCeleb2 is still not supported by torchaudio, so I wrote the implementation from scratch. I haven't tested it throughly, but I hope it can help you move ahead with your experiments. At least it should give you an idea on how to work with non-torchaudio datasets.
Let me know if you're able to try out the new datasets and, if so, whether you spot any bugs.
Thanks,
Alessio.
from titanet.
Related Issues (7)
- ValueError During Training Process HOT 3
- weights HOT 1
- training HOT 3
- voxceleb dataset HOT 1
- How to train on a custom dataset? HOT 1
- titanet.ipynb: session crashed for an unknown reason 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 titanet.