Comments (13)
syedasaraCodeNinja
commented on August 19, 2024
2
Did your model give reasonable predictions because the training loss is NAN in both steps?
from xlsr-wav2vec2-speech-recognition-urdu.
Bushramjad
commented on August 19, 2024
It's about 7 hours of recorded data, which was then split for training and testing.
from xlsr-wav2vec2-speech-recognition-urdu.
syedasaraCodeNinja
commented on August 19, 2024
Average duration of each audio?
from xlsr-wav2vec2-speech-recognition-urdu.
Bushramjad
commented on August 19, 2024
@syedasaraCodeNinja 2 sec each
from xlsr-wav2vec2-speech-recognition-urdu.
Asifm93
commented on August 19, 2024
I am training similar model to this model on other local language using colab pro 40 GB GPU still it says out of memory error ; Training data is around 4-7 hours. Can you connect with me to help out to your extent ; [email protected]
from xlsr-wav2vec2-speech-recognition-urdu.
syedasara98
commented on August 19, 2024
What is the duration of your each audio file?
I am training similar model to this model on other local language using colab pro 40 GB GPU still it says out of memory error ; Training data is around 4-7 hours. Can you connect with me to help out to your extent ; [email protected]
from xlsr-wav2vec2-speech-recognition-urdu.
Asifm93
commented on August 19, 2024
Min 2 sec max 55 sec
from xlsr-wav2vec2-speech-recognition-urdu.
syedasara98
commented on August 19, 2024
55 seconds is too large. The duration of audio file should be from 2 secs to 8 secs.
Secondly, change the "per_device_train_batch_size" from 16 to 8 or 4. The memory error could be because of large batch size
from xlsr-wav2vec2-speech-recognition-urdu.
Asifm93
commented on August 19, 2024
Yes tried different options still getting same can you have look at code if possible ?
from xlsr-wav2vec2-speech-recognition-urdu.
syedasara98
commented on August 19, 2024
Yeah sure.
from xlsr-wav2vec2-speech-recognition-urdu.
Asifm93
commented on August 19, 2024
alright just email when you have enough time thank you ; [email protected]
from xlsr-wav2vec2-speech-recognition-urdu.
Asifm93
commented on August 19, 2024
Yeah sure.
??
from xlsr-wav2vec2-speech-recognition-urdu.
Asifm93
commented on August 19, 2024
A.o.a,
Hope You'll be doing well. Kindly do a favor to look at code and guide
what's the issue if possible.
Thank you :)
Kind regards.
…On Thu, 25 May 2023 at 16:01, Syeda Sara ***@***.***> wrote:
Yeah sure.
—
Reply to this email directly, view it on GitHub
<#3 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/ALPTS5OO2LBOBO3CKJY3Q2LXH43Z7ANCNFSM52VBCTMA>
.
You are receiving this because you commented.Message ID:
<Bushramjad/XLSR-Wav2Vec2-Speech-Recognition-Urdu/issues/3/1562706559@
github.com>
from xlsr-wav2vec2-speech-recognition-urdu.
Related Issues (4)
- Datasets for Urdu HOT 5
- Urdu Dataset HOT 4
- Pre-trained model HOT 5
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 xlsr-wav2vec2-speech-recognition-urdu.