Metadata-Version: 2.4
Name: speechevalkit
Version: 0.1.0
Summary: A unified speech evaluation toolkit for speech generation, enhancement, and voice conversion.
Author-email: Your Name <your_email@example.com>
License: MIT
Project-URL: Homepage, https://github.com/iamshreeji-copy2/speechevalkit
Project-URL: Repository, https://github.com/iamshreeji-copy2/speechevalkit
Project-URL: Issues, https://github.com/iamshreeji-copy2/speechevalkit/issues
Keywords: speech,audio,evaluation,PESQ,STOI,SI-SDR,MCD,voice-conversion,speech-enhancement
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Science/Research
Classifier: Intended Audience :: Developers
Classifier: Topic :: Multimedia :: Sound/Audio :: Analysis
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENCE
Requires-Dist: numpy>=1.23
Requires-Dist: scipy>=1.9
Requires-Dist: librosa>=0.10
Requires-Dist: tqdm>=4.64
Requires-Dist: rich>=13.0
Provides-Extra: torch
Requires-Dist: torch>=2.0; extra == "torch"
Provides-Extra: true-metrics
Requires-Dist: pesq>=0.0.4; extra == "true-metrics"
Requires-Dist: pystoi>=0.4.1; extra == "true-metrics"
Provides-Extra: all
Requires-Dist: torch>=2.0; extra == "all"
Requires-Dist: pesq>=0.0.4; extra == "all"
Requires-Dist: pystoi>=0.4.1; extra == "all"
Dynamic: license-file

# SpeechEvalKit

🎧 **SpeechEvalKit** is a clean, lightweight Python toolkit for evaluating speech generation, speech enhancement, and voice conversion systems.

It provides a simple API, batch directory evaluation, automatic audio loading/resampling/alignment, robust error handling, progress bars, and a colorful CLI.

---

## Features

- Simple Python API
- Command-line interface
- Batch directory evaluation
- Automatic filename matching
- Audio loading and resampling
- Mono conversion
- Trim/pad alignment
- Robust handling of corrupted or missing files
- Progress tracking with `tqdm`
- Rich terminal output
- JSON result logging

---

## Metrics

SpeechEvalKit supports:

- `pesq`
- `stoi`
- `si_sdr`
- `mcd`
- `cosine`

### Note on PESQ and STOI

True PESQ and STOI require specialized third-party implementations.

SpeechEvalKit remains runnable with only the core dependencies. If optional packages are installed:

```bash
pip install pesq pystoi
