torchaudio
Audio signal processing library for PyTorch. Covers feature extraction (spectrograms, mel-scale), waveform manipulation, and GPU-accelerated data augmentation techniques. (torchaudio, melscale, spectrogram, pitchshift, specaugment, waveform, resample)
npx skills add majiayu000/claude-skill-registry --skill torchaudio-cuba6112-skillfactory-a7f85613 --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
## Overview TorchAudio provides signal processing tools for PyTorch, enabling users to treat audio processing as part of the neural network graph. This allow transforms to be run on GPUs and handled via `nn.Sequential` pipelines. ## When to Use Use TorchAudio for converting raw audio waveforms into features like Mel Spectrograms, performing data augmentation (SpecAugment), or when high-performance resampling is required. ## Decision Tree 1. Do you need to transform many audio files quickly? - MOVE: The transform module to GPU using `.to('cuda')`. 2. Are you training an Automatic Speech Recognition (ASR) model? - USE: SpecAugment (TimeMasking, FrequencyMasking) on the spectrogram. 3. Do you need to align text to audio? - USE: The `forced_align` functional API with a Wav2Vec2 model. ## Workflows 1. **Audio Feature Extraction Pipeline** 1. Load the waveform as a PyTorch tensor. 2. Apply `Resample` to match the target frequency (e.g., 16000Hz). 3. Use `Spectrogram` to convert to a power/amplitude scale. 4. Convert the spectrogram to mel-scale using `MelScale`. 5. Optionally apply `AmplitudeToDB` to get decibel values. 2. **GPU-Accelerated Data Augmentation** 1. Define an augmentation p
- Overview
- When to Use
- Decision Tree
- Workflows
- Non-Obvious Insights
- Evidence
- Scripts
- Dependencies
- References
What does the torchaudio skill do?
Audio signal processing library for PyTorch. Covers feature extraction (spectrograms, mel-scale), waveform manipulation, and GPU-accelerated data augmentation techniques. (torchaudio, melscale, spectrogram, pitchshift, specaugment, waveform, resample)
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill torchaudio-cuba6112-skillfactory-a7f85613 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.