FunASR: A Fundamental End-to-End Speech Recognition Toolkit

GitHub - alibaba-damo-academy/FunASR
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models.

alibabaの音声関連のモデル

Google Colaboratory

モデル

emotion2vec

EMOTION2VEC

公式のpytorch code

https://github.com/ddlBoJack/emotion2vec

JSONの例

https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav

[
  {
    "key": "rand_key_2yW4Acq9GFz6Y",
    "labels": [
      "生气/angry",
      "厌恶/disgusted",
      "恐惧/fearful",
      "开心/happy",
      "中立/neutral",
      "其他/other",
      "难过/sad",
      "吃惊/surprised",
      "<unk>"
    ],
    "scores": [
      1.2239316920798892e-15,
      1.990177528648496e-17,
      1.7794288657725418e-18,
      7.486658252435323e-15,
      1.0,
      2.0938180895225618e-18,
      3.173319151395827e-14,
      5.799354671930906e-17,
      2.0424456239896497e-18
    ]
  }
]