Whisper large-v3 requirements, license & speed

Key facts

License

apache-2.0 source

Commercial use

Yes source

HF card: Apache-2.0; GitHub repo: code and weights MIT

Parameters

1.54B source

safetensors parameter count

Minimum memory

~10 GB VRAM source

Runs on CPU

Unknown

Streaming

No source

30-second window encoder-decoder; real-time use needs a wrapper such as whisper_streaming

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 source

Released

2023-11-07 source

Hugging Face repo creation date (proxy for release date)

Gated on HF

No