ming024/FastSpeech2

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2185 stars · 616 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A PyTorch implementation of Microsoft's FastSpeech 2 text-to-speech model, supporting English and Mandarin with single- and multi-speaker synthesis. It includes pretrained checkpoints, MelGAN/HiFi-GAN vocoder support, and controllable pitch, volume, and speaking rate.

Use cases

• synthesize speech from text in Python
• train a FastSpeech 2 TTS model on LJSpeech
• build a multi-speaker English or Mandarin TTS system
• control pitch and speaking rate of generated speech
• generate audio samples with HiFi-GAN vocoder
• reproduce FastSpeech 2 research results

When to choose

• you need a FastSpeech 2 implementation with pretrained checkpoints
• you want controllable TTS with pitch/volume/rate adjustment
• you need multi-speaker TTS for English or Mandarin
• you want a PyTorch codebase to extend for TTS research

When to avoid

• you need the latest state-of-the-art TTS models like VITS or diffusion-based systems
• you want a production-ready TTS service with an API
• you need languages other than English or Mandarin
• you prefer a maintained library with active development

Facets

library · maturity maintenance

tts machine-learning deep-learning speech-processing deep-learning python cross-platform text-to-speech pytorch fastspeech2 vocoder melgan hifi-gan multi-speaker natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="ming024/FastSpeech2")