Comments (2)
If you want to finetune using the original tokenizer, yes you'll need to normalize all numbers to spoken words.
Changing tokenizer means you'll need a large amount of data to retrain the model, that is not suggested unless you have several thousand hours of speech to reach best results
from nemo.
If you want to finetune using the original tokenizer, yes you'll need to normalize all numbers to spoken words.
Changing tokenizer means you'll need a large amount of data to retrain the model, that is not suggested unless you have several thousand hours of speech to reach best results
How to use the original tokenizer?
I also created a discussion for this.
from nemo.
Related Issues (20)
- Latest huggingface transformers version breaking nlp modules HOT 6
- Any tts models in nemo that can simulated human laughter and other human sounds?
- setuptools 70.0.0 results in ImportError: cannot import name 'packaging' from 'pkg_resources' HOT 3
- Question about the settings in speech_data_simulator HOT 4
- The training hangs in the middle on multiple nodes, showing low power consumption and 100% GPU utilization.
- Request for Code and Models
- Issue Resuming Training from Checkpoint with Small Validation Dataset HOT 5
- Error: cannot import name 'ALBERT_PRETRAINED_MODEL_ARCHIVE_LIST' from 'transformers' while using HOT 4
- NameError: name 'ApexGuardDefaults' is not defined HOT 1
- Nvidia GPU is Not accessing in my Docker Container HOT 2
- why we reverse the RGB channels in video processor HOT 1
- Error(s): ConfidenceConfig.__init__() got an unexpected keyword argument 'measure_cfg' HOT 12
- ImportError: cannot import name '_library_root_logger' from 'apex' (unknown location)
- Citrinet Training: Sentences are cut during prediction HOT 1
- Unable to disable validation
- Why isn't FSDP supported by DistributedCheckpointIO?
- video input 'image_aspect_ratio=pad' not work
- Nemo_toolkit 2.0.0.rc0 installation failure HOT 12
- FSDP reduce_scatter can not overlap with compute
- Getting `TypeError: can't convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first.`
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.