PS-AI

Finetuning released model ( Exp 4) for new language

5

Hi, Thanks for your amazing contribution. I am trying to finetune the model of Exp 4 [https://drive.google.com/drive/folders/15G-QS5tYQPkqiXfAdialJjmuqZV0azQV] for a new language - Malayalam with the IndicTTS dataset following steps mentioned...

Import Error when running Examples 12, 13

2

The error is: ImportError: cannot import name 'normalize_features' from 'pyAudioAnalysis.audioTrainTest' (/usr/local/lib/python3.7/dist-packages/pyAudioAnalysis/audioTrainTest.py)

When try to run "pip install -r requirements.txt" in a virtual environment in WSL, I get this error: Failed to build mosestokenizer ffmpy flask-cachebuster docopt toolwrapper uctools Could you help...

Hi, When running preprocess.py, I get this error: RuntimeError: cuDNN error: CUDNN_STATUS_INTERNAL_ERROR Could you guide me on solving this? This is the stack trace: Loading hubert for content... load model(s)...

Hi, Thanks for your work. I am trying to run the training as mentioned in the Readme file. I am getting this error: RuntimeError: GET was unable to find an...

How to resume training

4

Hi, Thank you for your work. I was able to follow the steps given in Readme.md file and start training the autoregressive.pth. But, my training crashed mid-way due to lack...

Takes too much VRAM to transcribe audios

20

Hi, Thank you for your work. I tested CrisperWhisper today with an audio of 2 minute duration on a NVIDAI A100 GPU. The model VRAM footprint is only 3.5GB which...