faster-whisper (large-v3, CTranslate2) requirements, license & speed

Key facts

License

mit source

Commercial use

Yes source

MIT

Parameters

1.55B source

same weights as Whisper large-v3, converted to CTranslate2

Minimum memory

~2.9 GB VRAM (large-v2, int8, beam 5, project benchmark) source

Project benchmark used large-v2, not v3; fp16 used ~4.5 GB

Runs on CPU

Yes source

int8 CPU inference supported

Streaming

No source

Not built-in; README lists third-party streaming projects (Whisper-Streaming, WhisperLive)

Voice cloning

n/a (speech-to-text)

Languages

en, zh, de, es, ru, ko, fr, ja, pt, tr, pl, ca, nl, ar, sv, it, id, hi, fi, vi, he, uk, el, ms, cs, ro, da, hu, ta, no, th, ur, hr, bg, lt, la, mi, ml, cy, sk, te, fa, lv, bn, sr, az, sl, kn, et, mk, br, eu, is, hy, ne, mn, bs, kk, sq, sw, gl, mr, pa, si, km, sn, yo, so, af, oc, ka, be, tg, sd, gu, am, yi, lo, uz, fo, ht, ps, tk, nn, mt, sa, lb, my, bo, tl, mg, as, tt, haw, ln, ha, ba, jw, su, yue source

Released

2023-11-23 source

Hugging Face repo creation date (proxy for release date)

Gated on HF

No