Installation steps
- Cloning Project Warehouse:
git clone https://github.com/yangb05/PengChengStarling cd PengChengStarling - Install the dependencies:
pip install -r requirements.txt export PYTHONPATH=/tmp/PengChengStarling:$PYTHONPATH
Usage Process
Data preparation
Run the prepare.py script to adapt the data format and generate the data.list file and associated features.
model training
- Configure parameters in the config_train directory
- Execute training commands
./train.sh
speech recognition
- Prepare the audio file to be recognized
- (of a computer) run
./eval.shinference
Recommendations for fine-tuning
If there is a need to improve recognition accuracy in a specific area:
- Relevant data in the area of preparedness
- fulfillment
./train.sh --finetunefine tune - Fine-tuned model ready for deployment
This answer comes from the articlePengChengStarling: Smaller and Faster Multilingual Speech-to-Text Tool than Whisper-Large v3The
May not be reproduced without permission:AI productivity tools " How to install and use PengChengStarling for speech to text?
