Comments (3)
Oktai15
commented on May 18, 2024
1
@okuchaiev @Giuseppe5 what was the main difference between 0.9 and 0.8.2 to reproduce LibriSpeech results? I have the same problem with current master.
from nemo.
okuchaiev
commented on May 18, 2024
Are you using master version of NeMo? It is not compatible with published checkpoints. Could you please try the latest stable version 0.8.2 which you’ll get if you just install from pip (or take 0.8.2 tag on git) Published checkpoints correspond to the latest stable version.
(master is 0.9 which is WIP and will be released soon)
from nemo.
Giuseppe5
commented on May 18, 2024
Starting from 0.8.2 everything seems to work just fine, with results that are slightly better than the ones reported on the paper for dev_clean.
Thank you for your time and answer!
from nemo.
Related Issues (20)
- `megatron_gpt_finetuning.py` does not work `max_epochs` HOT 1
- Is frame marblenet VAD still supported?
- Context parallel does not work in some cases which works well using megatron-lm directly
- Can't train/finetune a model on two RTX4090
- is Forced Alignment available on prebuilt Docker images? HOT 1
- Support for Specifying Start and End Time when Reading WAV File HOT 1
- Saving and reloading the pretrained model's vocab breaks the tokenizer. HOT 2
- IndexError: index -1 is out of bounds for dimension 1 with size 0
- Support required for fine tuning cache aware streaming model
- Canary model stuck in a loop? Just repeats the same phrases over and over. HOT 2
- Slow training on Mixtral-8x22B when DP size > 1 HOT 2
- TypeError: EncDecRNNTBPEModel.change_vocabulary() got an unexpected keyword argument 'new_vocabulary' HOT 1
- Memory Allocation Error during alignement (tools/nemo_forced_aligner/align.py)
- "greedy_batched" methods should support "partial_hypotheses" option
- problem in exp_manager
- ImportError: cannot import name '_is_local_file_protocol' from 'pytorch_lightning.callbacks.model_checkpoint' HOT 1
- "FileNotFoundError: KenLM binary file not found at : None" thrown when decoding without N-gram LM
- GPU Limit Error when using stt_multilingual_fastconformer_hybrid_large_pc model for long audio file (55 minutes) HOT 3
- Flashlight decoder for ASR HOT 4
- nemo2riva export doesn't work with FastPitch HOT 3
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 nemo.