| { |
| "model": "Streaming Sortformer 4-spk v2 (NVIDIA)", |
| "license": "cc-by-4.0", |
| "sample_rate": 16000, |
| "n_mels": 128, |
| "n_fft": 512, |
| "win_length": 400, |
| "hop": 160, |
| "preemph": 0.97, |
| "normalize": "NA", |
| "mag_power": 2.0, |
| "log_guard": 5.960464477539063e-08, |
| "pad_to": 16, |
| "subsampling_factor": 8, |
| "frame_hop_ms": 80, |
| "n_spk": 4, |
| "spkcache_len": 188, |
| "fifo_len": 0, |
| "chunk_len": 188, |
| "chunk_left_context": 1, |
| "chunk_right_context": 1, |
| "spkcache_update_period": 188, |
| "spkcache_sil_frames_per_spk": 3, |
| "scores_boost_latest": 0.05, |
| "sil_threshold": 0.2, |
| "pred_score_threshold": 0.25, |
| "strong_rate": 0.75, |
| "weak_rate": 1.5, |
| "min_pos_rate": 0.5, |
| "max_index": 99999, |
| "tf_max": 1520, |
| "spk": 188, |
| "pe_max": 190, |
| "t": 378, |
| "graph_io": "chunk_mel[1,1520,128],spkcache[1,188,512],valid[1,378] -> preds[1,378,4],chunk_pe[1,190,512]", |
| "golden": { |
| "mel_shape": [ |
| 128, |
| 2160 |
| ], |
| "mel_len": 2150, |
| "total_preds_shape": [ |
| 270, |
| 4 |
| ] |
| }, |
| "note": "host: NeMo 128-mel (preemph->stft512/win400/hop160->slaney mel->log, normalize=NA) -> feat_chunks (188*8, L/R ctx 1) -> per chunk zero-pad mel to 1520, build spkcache(188)+valid, run graph, slice chunk preds, streaming_update + AOSC compress_spkcache; threshold 0.5/frame/spk (frame=80ms) -> speaker turns." |
| } |
