Same recording, four methods: who said what?

Play the audio and follow the subtitles. Each word is colored by the speaker that method assigned; a red underline means it disagrees with ground truth. Source: Harper Valley Bank (CC BY 4.0) — no patient audio.
What each method knows: AWS and W+ECAPA self-enrolled are fully blind — profiles come from the recording's own clusters, with no outside reference audio. W+ECAPA enrolled and FT v2 were given about 20 s of reference audio from each person's clean channel — available for care partners in the archive, rarely for patients. Compare the first two for a fair test, the last two to see what enrollment adds.
Scores

Subtitles

Extraction quality — pretrained vs our fine-tunes

A different question, and the one extraction is actually built for: on a natural call, how cleanly does the model pull out one person? Three held-out Harper Valley calls, agent enrolled. Scores are SI-SNR in dB while the target speaks alone (higher is better), and the other speaker's residue (lower is better). The pretrained model was the best of three off-the-shelf options; the fine-tunes are ours.

FT v2 — extracted audio

The other methods only label; they never split the audio. FT v2 actually extracts it — this is the per-person output.

Transcript quality — per-speaker accuracy

Of each speaker's reference transcript, how much did each method get right? Accuracy (100 − WER), higher is better; best per row highlighted. MOSS and AWS are single-pass systems; W+ECAPA splits one Whisper pass; DiCoW re-runs conditioned ASR per speaker; FT v2 extracts audio then transcribes.
casespeakerMOSSAWSW+ECAPADiCoWFT v2
two men (1%)speaker 1%100.0%95.2%95.2%72.6%53.2
two men (1%)speaker 2%100.0%86.0%86.0%64.0%42.0
two women (5%)speaker 1%86.9%63.1%66.9%67.7%66.2
two women (5%)speaker 2%77.6%52.0%58.2%72.4%24.5
dense overlap (47%)speaker 1%19.0%1.6%3.2%46.0%44.4
dense overlap (47%)speaker 2%90.5%90.5%88.1%95.2%92.9
three speakers (55%)speaker 1%11.7%0.0%0.0%5.0%28.3
three speakers (55%)speaker 2%45.0%0.0%5.0%62.5%17.5
three speakers (55%)speaker 3%57.1%61.9%47.6%52.4%64.3
Two regimes, two winners. On natural calls MOSS is the clear leader (78–100% accuracy). On heavily overlapped speech, DiCoW — Whisper conditioned on the diarization mask — is the only method that writes the masked speaker as text (46% accuracy vs 2–3% for every labeling approach), matching audio extraction while beating it on the dominant speaker. DiCoW's catch: it needs a diarization input (pyannote, the slowest stage) and its released code pins old library versions.

Speed

Measured end to end on the 107 s two-men call, one laptop CPU, no GPU — except the MLX row, which is the same laptop's Apple GPU. Model loading (about 8 s total) excluded.
stagetimevs real time
Whisper large-v3-turbo (words)27.5 s3.9x
pyannote (clustering)96.3 s1.1x
ECAPA (423 sliding windows)9.3 s11.5x
SpeakerBeam FT v2 (one speaker)25.5 s4.2x
MOSS (no stages — one pass replaces all of the above)93 s CPU · 8.2 s MLX1.2x · 13.1x
full pipeline107 s callvs real time
W+ECAPA enrolled (no pyannote)36.8 s2.9x
MOSS end-to-end (one pass, no pyannote, no Whisper)93 s1.2x
MOSS 8-bit MLX (same weights, Apple GPU, single pass)8.2 s13.1x
DiCoW (pyannote 96 s + conditioned ASR 80 s)176 s0.6x
W+ECAPA self-enrolled133.1 s0.8x
plus FT v2 on both speakers184.1 s0.6x
Pipeline totals for 107 s of audio: W+ECAPA enrolled 36.8 s (2.9x) · W+ECAPA self-enrolled 133.1 s (0.8x) · plus FT v2 on both speakers 184.1 s (0.6x).
pyannote is the bottleneck — it costs more than everything else combined. A CP voice profile removes it from the pipeline, which is why enrollment is worth about 3.6x in speed on top of what it does for accuracy.
The 8-bit MLX build changes the picture entirely: the same MOSS pass at 13x real time, transcript and speaker labels identical to the full-precision output on our test files — fast enough that one small GPU covers production volume.