AutoArk/open-audio-opd

Health v2 · maintenance only

Flags: no_releases young no_license

Adoption not part of the score

1007 stars · 62 forks observed · 2026-08-28

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

An industrial training stack for online policy distillation (OPD) of audio models, distilling compact ASR (and planned TTS) student models from stronger teacher models using token-level KL on top-k support. It builds on THUNLP/OPD and a vendored copy of verl, with FSDP2 distributed training support.

Use cases

• distill a compact ASR model from a larger teacher model
• run online policy distillation training for speech recognition
• train audio models with FSDP2 distributed training
• reproduce the ARK-ASR-0.6B training recipe
• apply teacher-scored token-level KL training to speech models
• set up an on-policy rollout training pipeline for audio models

When to choose

• you need to distill a small ASR model from a stronger teacher with on-policy rollouts
• you want a production-style audio distillation stack with FSDP2 distributed training
• you're researching online policy distillation for speech recognition

When to avoid

• you need a ready-to-use inference or ASR API rather than a training stack
• you need TTS distillation today - it's still on the roadmap
• you want a framework that ships with datasets or audio files - all data paths are user-supplied

Facets

library · maturity active

llm-training speech-recognition tts machine-learning gpu-computing speech-processing machine-learning deep-learning python knowledge-distillation online-policy-distillation asr tts fsdp2 distributed-training verl training-stack audio gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="AutoArk/open-audio-opd")