README.md

s2s-a0-en — Stage-A0 training grids for a small duplex S2S model

Format per tokens/a0_*.npz:

• audio int16 [T,16] — Mimi codes @12.5Hz, 8 codebooks: cols 0-7 = speech ("agent" channel), cols 8-15 = encoded silence ("user" channel)
• text int32 [T] — Qwen3-0.6B token ids, run-length from each utterance's start frame; pad elsewhere
• prompt_len = 0, source = "a0_" Utterances packed to ~100s per grid with 0.2-0.4s gaps. No delay/lead applied. manifests/*.json map each source parquet file to its grids + hours. See ATTRIBUTION.md for source datasets and licenses.