Using statistical methods to determine speech femininity/masculinity based on phonetic features
Project description
SpeechGenderAnalysis
Setup
MacOS
1. Setup Python:
python3.8 -m venv venv8
source venv8/bin/activate
pip3 install -r requirements-mac.txt
2. Configure plaidml
to use GPU:
plaidml-setup
3. Configure environment variables in the run script:
export KERAS_BACKEND="plaidml.keras.backend"
export tg_token="Your telegram token here"
Windows (CUDA)
1. Setup Python
python3.9 -m venv venv
.\venv\Scripts\activate
pip install -r requirements-win-cuda.txt
2. Install CUDA
- Install NVIDIA Drivers: https://www.nvidia.com/drivers
- Install CUDA 11.2 (for TensorFlow 2.7.0): https://developer.nvidia.com/cuda-toolkit-archive
- Download cuDNN 8.1: https://developer.nvidia.com/rdp/cudnn-archive
- Copy folders in
cudnn-11.2-windows-x64-v8.1.1.33\cuda
toC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.2
- Copy folders in
- Restart IntelliJ IDEA
3. Check Device List
python -c "from tensorflow.python.client import device_lib; print(device_lib.list_local_devices())"
Arch Linux (CUDA)
Python (3.9.11)
python -m venv venv
source ./venv/bin/activate
pip install -r requirements-win-cuda.txt
sudo pacman -S tensorflow-cuda
python -c "from tensorflow.python.client import device_lib; print(device_lib.list_local_devices())"
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Close
Hashes for speech-gender-statistics-1.0.1.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 53f89ce40821849e1d11d7e49bcb71a5442c1e1ca7127aa9bff11eec475282f2 |
|
MD5 | 97898bb3ffda6884f0d9817365bfce9a |
|
BLAKE2b-256 | da88f2cf71190db0c2279ca9a5a40d9b0742d96f470e6366175d53116dda5206 |
Close
Hashes for speech_gender_statistics-1.0.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | b2995ad3f378f1f508d36927163c1befd1d35de17e86ee8d0413853162f8238a |
|
MD5 | 1ad4e37be4032fcd9a205e113e431eb4 |
|
BLAKE2b-256 | e0d170fce1c07d5571e476830f8f47b97f0108bfd614b486928e2af8e2d0bb51 |