Comments (4)
bmilde
commented on August 12, 2024
2
Nearly ready! I'm currently running into problem similar to https://groups.google.com/forum/#!topic/kaldi-help/BxvNZuxTgz0 but that seems to be an OpenBLAS bug. I'll push the added code once the TDNN training runs.
from kaldi-tuda-de.
bmilde
commented on August 12, 2024
Hi!
Ive already prepared most of necessary scripts, havent pushed it yet. Its
comming very soon! But if you want to help me test it, I'd welcome that.
Let me know,
Best,
Benjamin
Botium <[email protected]> schrieb am Sa., 4. Jan. 2020, 18:24:
… Hi,
Is there a special reason why the Mozilla common voice is not part of this
recipe ? Maybe licensing issues ?
If I prepared a pull request adding Mozilla common voice corpus to this
recipe, would you accept it ?
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub
<#34?email_source=notifications&email_token=ACKGA6UIPEPIDO2EGFV75J3Q4DA43A5CNFSM4KCXBFI2YY3PNVWWK3TUL52HS4DFUVEXG43VMWVGG33NNVSW45C7NFSM4IEAYKPQ>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/ACKGA6WZ4TIDKUYTDZ56XALQ4DA43ANCNFSM4KCXBFIQ>
.
from kaldi-tuda-de.
codeforequity-at
commented on August 12, 2024
Absolutely. I suggest pushing to a feature branch so I can checkout to my machine.
On another note, I am currently preparing a Dockerfile to make this recipe work without having to install all the requirements manually. Maybe this would be a good contribution.
from kaldi-tuda-de.
bmilde
commented on August 12, 2024
I've added common voice to the training data (1000h in total now!). We also have a new LM based on https://github.com/bmilde/german-asr-lm-tools
Have you had success with the Dockerfile?
from kaldi-tuda-de.
Related Issues (20)
- G.fst error , bad FST header HOT 4
- tree for pretrained chain model HOT 2
- Kaldi data preprocessing HOT 1
- New German model is arrived (Kaldi_tuda_de) HOT 5
- oov words (after g2p) HOT 12
- Issues executing run.sh HOT 3
- run.sh failing: text contains 103359 lines with non-printable characters HOT 4
- General questions about project
- Where is cuda_cmd used
- local/run_ivector_common.sh: expected file data/train_cleaned/feats.scp to exist HOT 10
- sox FAIL formats: sox not able to handle common_voice mp3. Is there any solution? HOT 5
- language model issue. kaldi_lm is not in path HOT 12
- Spacy v3 does not support loading from alias any more HOT 2
- Tree file for pre-trained models? HOT 1
- Number in Train set HOT 2
- Additional German speech training data HOT 1
- Common Voice 7.0? HOT 3
- missing dictionary files HOT 1
- New words?
- RROR (fstisstochastic[5.5.1077~1-ed31c6]:ReadFstKaldiGeneric():kaldi-fst-io.cc:59) Reading FST: error reading FST header from
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 kaldi-tuda-de.