Search Results for "waveform" - Page 2

...It introduces a generator architecture tailored to model the periodic structure of speech and a set of discriminators that focus on different scales and periods of the waveform to better capture naturalness. The model targets a sweet spot between sample quality and generation speed, outperforming many previous GAN vocoders while being far faster than typical autoregressive models. In experiments on LJSpeech, HiFi-GAN was shown to achieve mean opinion scores close to human recordings while synthesizing 22.05 kHz audio up to ~168× faster than real time on an NVIDIA V100 GPU. ...

...The repository is structured as a full training pipeline: dataset preparation, preprocessing into spectrograms, Tacotron training, WaveNet (or Griffin-Lim) vocoder training, and final waveform synthesis. It includes directory layouts and logging directories for multiple datasets such as LJSpeech and M-AILABS en_US/en_UK, making it easier to adapt to new English corpora. Separate log trees track mel-spectrograms, attention plots, evaluation audio, and vocoder outputs, so you can inspect how alignment and audio quality evolve over time.

...The model is split into two networks: Text2Mel, which maps text to mel-spectrograms, and SSRN (spectrogram super-resolution network), which converts low-resolution mel-spectrograms into high-resolution magnitude spectrograms suitable for waveform synthesis. Training scripts, data loaders, and hyperparameter configurations are provided to reproduce results on several datasets, including LJ Speech for English, a Korean single-speaker dataset, and audiobook data from Nick Offerman and Kate Winslet.

This program written in Python is used for capture screenshot or raw data from a UNI-T digital storage oscilloscope.

wfProc is going to be a Python module for waveform processing. The module will incude simple operations such as addition, subtraction etc, taking into account the timeline of the waveform, as well as filtering, fft and other more complex operations.

...The input files for SpiKeDeteKt are: .dat (raw data file) .probe (probe file, described below - user constructed) parameters.py (optional - otherwise it uses defaultparameters.py) SpiKeDeteKt outputs the following files: .fet.n (feature file) .mask.n (needed for using the new (masked) KlustaKwik) .clu.n (a trivial clue file where everything is put into a single cluster) .fmask.n (trial - float masks instead of binary, we are using this for testing masked KlustaKwik) .spk.n (spike file) .upsk.n (unfiltered spike waveform) .res.n (list of spike times) .xml (an xml file with all the parameters that can subsequently be used by neuroscope or klusters) .fil (highpass filtered data) .h5 (

AudiOpen is a framework and GUI for audio synthesis, with the goal of developing an environment where obtaining the waveform you want is very intuitive by taking a very systematic/mathematical approach to defining audio and supporting Python scripts.

QWave: Qt-based waveform display and audio playback class library.

Function graph drawing/rendering application for use with audio applications. Exports .wav files. Dependencies: wxPython & Numeric(not in 1.10)