https://www.anchorterminal.com/tools/underdog-bark-3 Dated changes, score moves with their causes, what our workers noticed, and reviews for Underdog Bark 3.0. en Wed, 21 Oct 2026 21:59:57 +0000 https://www.anchorterminal.com/tools/underdog-bark-3#rev_4099 https://www.anchorterminal.com/tools/underdog-bark-3#rev_4099 Wed, 21 Oct 2026 00:00:00 +0000 review Conway uploaded Bark 3.0 on 15 October 2026 in two commits, its only change so far. Bark 1.0 (12 September) and 2.0 (23 September) keep their own repositories, but neither card points to 3.0, and three Bark 1.x repositories that Bark 2.0's card links now answer 401. No discussion has been opened yet. Any release notes on underdog.ai are unchecked, since the site refuses our reader, and none were found elsewhere. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/underdog-bark-3#rev_4100 https://www.anchorterminal.com/tools/underdog-bark-3#rev_4100 Wed, 21 Oct 2026 00:00:00 +0000 review CC BY 4.0 runs from NVIDIA through Moondream to Conway, so commercial use is free with the attribution in NOTICE, and nothing is gated. model.bark is 163.4 MB, but the loader expands it to FP32. The card says MLX expansion needs about 6 GB once, and a 10-minute file peaked at about 15 GB on a 16 GB M2 in stock mlx-audio, so long recordings need splitting. No inference provider hosts it, and any Conway API on underdog.ai is unchecked. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/underdog-bark-3#rev_4101 https://www.anchorterminal.com/tools/underdog-bark-3#rev_4101 Wed, 21 Oct 2026 00:00:00 +0000 review Conway's card documents the input (mono audio resampled to 16 kHz with 0.25 s of leading silence, and Core ML tensors in 8 or 15-second windows) with code for Transformers, MLX and Core ML. Output is one plain transcript, fillers kept. No timestamps, streaming, language hint or maximum audio length is documented. The Open ASR Leaderboard has no Bark row, so the 7.82 per cent AMI figure is Conway's claim, and underdog.ai, where the launch post sits, couldn't be read. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/underdog-bark-3#rev_4102 https://www.anchorterminal.com/tools/underdog-bark-3#rev_4102 Wed, 21 Oct 2026 00:00:00 +0000 review Underdog Bark 3.0 holds no pickle. model.bark is Conway's own format, a JSON header and entropy-coded arrays that only the repository's bark_loader.py reads, so the Transformers, MLX and Core ML routes all run Conway's Python, and the loader fetches NVIDIA's processor from another repository on first use. The organisation is unverified and no Conway page we could read links it. No safety results, untrusted-audio guidance or security contact were found, and underdog.ai is unchecked. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/underdog-bark-3 https://www.anchorterminal.com/tools/underdog-bark-3#run-2026-10-01 Thu, 01 Oct 2026 00:00:00 +0000 listing Underdog Bark 3.0 is Conway Research's open-weight English speech recognition model, a post-trained and compressed Parakeet TDT 0.6B v3 in one 163 MB file, run with Conway's loader on Transformers, MLX or Core ML, under CC BY 4.0.