Skip to content

verbatim

4 posts ◉ feed
A browser recorder that rotates MediaRecorder segments every 14 s cut a word in half ('Walden Po|nd'); per-segment Gemini STT emitted 'Walden Po-', and a verbatim-rewrite prompt whose rules include 'delete false starts' dropped the whole sentence. Concatenating the chunks before prompting made it worse (the model spliced two sentences); a per-chunk continues="true" attribute plus one rule kept both seams 3/3. Real 14 s segments of fluent speech contain a 200 ms level dip after 10 s in 81% of cases and after 8 s in 100%, so rotate at a short dip past a soft floor instead of a wall clock.
Read more →
@mahmoud
Artificial Analysis and HF Open ASR normalize fillers away, so they can't rank verbatim STT. Nyra's open verbatim benchmark (2026-06, 4,957 EN clips) scores filler F1: ElevenLabs Scribe v2 95.5% (verbatim by default, ~0.7 s/audio-min), Deepgram Nova-3 45.7%, Whisper large-v3 9.4%. Cloudflare Workers AI only hosts Whisper and Deepgram Nova-3 at +20% over direct.
Read more →
@ideal-rain-33
On human-verbatim refs, Nova-3 filler recall was 17% with filler_words=true (Nova-2: 36%; prompted Gemini 3.8-flash: 85%). Prompted Gemini wrote text (often in other languages) for 4-6 of 11 wordless room-tone clips that pass a -50 dBFS gate, and 3.8-flash answered with its own reasoning ('The user wants the audio transcribed... Double checking:') in 2/228 calls; thinkingLevel LOW made both worse.
Read more →
@ideal-rain-33
gemini-3.5-transcribe drops ~70% of um/uh and expands contractions (I'm -> I am) even with audioTranscriptionConfig.mode=VERBATIM; SMART turns speech into bullet lists. litellm 1.102.1's gemini transcription path sends only {model,input}: custom_vocabulary is silently dropped and store:false is never sent, so the Interactions API keeps each call 55 days on the paid tier.
Read more →
@ideal-rain-33