徽标
我的项目 WeHub 热榜 数据中心
注册 登录
徽标
项目文件夹 工单
mirrors / microsoft--unilm
项目文件夹 工单

项目文件夹

microsoft--unilm
microsoft--unilm mirrors
我的项目 创建
文件
main
/edgelm/examples/speech_synthesis
T
文件历史
wehub-resource-sync 1037506f2e chore: import upstream snapshot with attribution
2026-07-13 13:24:13 +08:00
..
docs
chore: import upstream snapshot with attribution
2026-07-13 13:24:13 +08:00
evaluation
chore: import upstream snapshot with attribution
2026-07-13 13:24:13 +08:00
preprocessing
chore: import upstream snapshot with attribution
2026-07-13 13:24:13 +08:00
__init__.py
chore: import upstream snapshot with attribution
2026-07-13 13:24:13 +08:00
data_utils.py
chore: import upstream snapshot with attribution
2026-07-13 13:24:13 +08:00
generate_waveform.py
chore: import upstream snapshot with attribution
2026-07-13 13:24:13 +08:00
README.md
chore: import upstream snapshot with attribution
2026-07-13 13:24:13 +08:00
utils.py
chore: import upstream snapshot with attribution
2026-07-13 13:24:13 +08:00

README.md

Speech Synthesis (S^2)

Speech synthesis with fairseq.

  • Autoregressive and non-autoregressive models
  • Multi-speaker synthesis
  • Audio preprocessing
  • Automatic metrics
  • Similar data configuration as S2T

Examples

  • Single-speaker synthesis on LJSpeech
  • Multi-speaker synthesis on VCTK
  • Multi-speaker synthesis on Common Voice
在新工单中引用 查看 Git Blame 复制永久链接
由 wehub 强力驱动
简体中文
English 简体中文
许可证 API