Whisper-large-v3 (OpenAI)

多语言语音识别与翻译，零样本泛化

入选理由: Whisper large-v3是开源ASR标杆，支持多语言识别与翻译，有现成pipeline和HF推理接口，精度较v2提升10-20%，适合高精度转写与多语言场景。
对位: 对位 Whisper large-v2
适合: 多语言语音转录 / 语音翻译为英文
不适合: 低延迟实时转录
规模: 1.55B · 30s 音频 · Q4 ~1GB / FP16 ~3.7GB
授权: Apache 2.0 · 需自查
框架: transformers / faster-whisper / whisper.cpp / openai-whisper
可信度: HuggingFace 下载量 549 万+, OpenAI 官方发布

评分详情

作者: openai
任务类型: automatic-speech-recognition
推理库: transformers
下载: 5,497,354
点赞: 6,100
许可证: Apache 2.0
标签: transformers, pytorch, jax, safetensors, whisper, automatic-speech-recognition, audio, hf-asr-leaderboard, 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, arxiv:2212.04356, license:apache-2.0, eval-results, endpoints_compatible, region:us, deploy:sagemaker, deploy:azure