Independent publisher
Erfan Roudaki
ErfanRou
Compare the published evidence
This profile connects the 2 model and dataset records shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.
Models
Datasets
Persian call-centre ASR silver set: the ErfanRou/callcc-ft150-soniox schema plus two auxiliary columns. Machine-labelled, not ground truth. Built by callcc-silver-5k/sonioxpipeline.py from markmuller/call-center-prod-data: 8 kHz stereo telephony split client-side into agent = channel 0 and customer = channel 1, each channel transcribed separately by Soniox stt-async-v5, words packed into 5-28 s windows (~15 s mean, natural pauses kept, short backchannels kept and padded with their own line silence), cut in silence and stored as 16 kHz mono FLAC. text — training target: Soniox words of the window, normalised (digits→words, Persian ی/ک, no punctuation, ZWNJ kept). textraw — the same words as…