Posts tagged with "Cuda"

OpenAI Whisper Speech Recognition Guide

Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification.

GitHub Repository

Installation

pip install git+https://github.com/openai/whisper.git 

Fix CUDA not detecting GPU

pip uninstall torch
pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu116

Example usage

# Transcribe
whisper input.mp3 --model medium.en --language en --task transcribe
# Translate
whisper japanese.wav --model large --language Japanese --task translate

Available models and languages

There are five model sizes, four with English-only versions, offering speed and accuracy tradeoffs. Below are the names of the available models and their approximate memory requirements and relative speed.

MiDaS Depth Estimation Guide

GitHub Repository

During installation, I ran into an issue where the CUDA package wasn’t found. Had to modify environment.yaml to:

name: midas-py310
channels:
  - pytorch
  - defaults
dependencies:
  - nvidia::cuda-toolkit=11.7.0
  - python=3.10.8
  - pytorch::pytorch=1.13.0
  - torchvision=0.14.0
  - pip=22.3.1
  - numpy=1.23.4
  - pip:
    - opencv-python==4.6.0.66
    - imutils==0.5.4
    - timm==0.6.12
    - einops==0.6.0

Commands that were helpful for troubleshooting CUDA: