VibeVoice-ASR-Streaming-7B-DFlash2-Drafter

A DFlash 2 block drafter for VibeVoice-ASR-Streaming-7B (Ar4ikov/VibeVoice-ASR-Streaming-7B-AWQ-W4A16-ASYM), for speculative decoding in vibevoice.c. It proposes 8 tokens in one pass; vibevoice.c checks them in one pass of the model and keeps the ones the model agrees with, plus one of its own.

The check is exact: every checked row is computed with the arithmetic of the model's own one-token decode step, so the transcript with this drafter is byte-for-byte the transcript without it — words, timestamps, speakers. The drafter only changes how many passes it takes.

Use

Needs vibevoice.c with DFlash 2 support: branch dflash2 (PR #48), in the next release. The model and this drafter in one download: Ar4ikov/VibeVoice-ASR-Streaming-7B-AWQ-W4A16-ASYM-DFlash2 (the INT4 drafter in drafter/, used without --draft).

vv_cli --model ./VibeVoice-ASR-Streaming-7B-AWQ-W4A16-ASYM --audio talk.wav --draft ./VibeVoice-ASR-Streaming-7B-DFlash2-Drafter
vv_cli serve --model ./VibeVoice-ASR-Streaming-7B-AWQ-W4A16-ASYM --draft ./VibeVoice-ASR-Streaming-7B-DFlash2-Drafter --slots 4           # streaming sessions (WebSocket, SSE) too

flag
--draft <dir>	this repository
--draft-block <n>	rows of the drafted block the model checks per pass (the drafter drafts 8; without the flag: 4 or 8, whichever keeps more tokens per ms)
--draft-check exact|fast	exact (default): the transcript without a drafter on the same --attn, bit for bit; fast: flashinfer attention and prefill projections for the check, the greedy transcript within rounding
--draft-quant int4|f16	how the runtime holds a BF16 drafter (INT4 by default)

It drafts for any VibeVoice-ASR-Streaming-7B checkpoint of the same model — microsoft/VibeVoice-ASR-Streaming-7B — since it reads only the model's hidden states, embedding and LM head; it was trained on the AWQ checkpoint's transcripts, so that is where it drafts best.

Results

vibevoice.c b72be15 (branch dflash2), RTX 3090, VibeVoice-ASR-Streaming-7B-AWQ-W4A16-ASYM, greedy decoding, decode tokens per second:

	plain	drafted	speedup	tokens per block	same transcript
20 held-out clips, 8 rows	149 tok/s	365 tok/s	2.45x	3.56	20/20
2-minute file, 8 rows	151 tok/s	390 tok/s	2.59x	3.72	yes
2-minute file, 4 rows	151 tok/s	316 tok/s	2.10x	2.85	yes
32-minute file, 8 rows	131 tok/s	275 tok/s	2.10x	3.54	yes
32-minute file, 4 rows	131 tok/s	252 tok/s	1.92x	2.76	yes

Streaming sessions (22 + 4 frames a chunk); plain = the same binary without --draft, decode tokens per second, --draft-check exact.

The drafter

• DFlash 2: 5 Qwen3-style layers (hidden 3584, 28/4 heads, intermediate 9472), 831M parameters, block 8.
• KV injection: for every position the model has processed, the outputs of its layers 1, 7, 13, 19 and 25 are concatenated, projected (fc) and normalized; every drafter layer turns them into keys and values. The drafter reads the model's own view of the audio and of the transcript so far.
• Two-tap dynamic convolution around attention and MLP (per-row kernels predicted from the row), and a candidate selector that re-ranks the model head's top 16 per row with a pairwise predecessor/successor term (rank 256).
• The embedding and the LM head are the model's, frozen. The drafter scores a draft vocabulary of 32768 ids (draft_vocab): the ids its training transcripts use, plus every stop id.
• Accepted drafts on 43 held-out clips' traces: 3.518 tokens per block of 8 (the selector's, with every earlier draft right).

Training

Self-distillation: the drafter learns what this model writes, timestamps and speaker ids included. tools/dflash in vibevoice.c holds the pipeline:

1. ~140 hours of audio, 2872 training clips and 43 held out, from LibriSpeech, FLEURS (8 languages), SOVA, AMI, earnings calls and VoxConverse — audio only; the datasets' own text is never used.
2. The model's own greedy transcripts of every clip (vv_dflash_data gen).
3. Traces: every position's token, its role and the five tapped layers' outputs, replayed through the runtime as streaming sessions (vv_dflash_data trace).
4. train.py (PyTorch, flex attention): anchors at generated positions, rows 1..7 scored against the next 7 tokens with weights e^(-k/4); cross-entropy of the head plus the selector's; AdamW, cosine schedule, BF16.

Limits

• vibevoice.c only: the checkpoint keeps the published DFlash 2 names, but the KV injection, the selector and the draft vocabulary are as vibevoice.c implements them (docs/DFLASH.md).
• CUDA only (the CPU path and Metal decode without the drafter). Greedy only.
• Audio the corpus covered little (Mandarin, Russian) keeps fewer drafts; the runtime then falls back to plain steps and stays near plain speed.

License

MIT, like VibeVoice.