StarMirror/MockingBird
1
0
Fork 0
mirror of https://github.com/babysor/MockingBird.git synced 2024-03-22 13:11:31 +08:00
Code Issues Projects Releases Wiki Activity

Update demo and training param

Browse Source 
A
This commit is contained in:
babysor00 2021-10-05 10:48:54 +08:00
parent b46e7a7866
commit 547ac816df
3 changed files with 11 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README-CN.md
View File

@ -5,7 +5,7 @@
### [English](README.md) | 中文 ### [English](README.md) | 中文
### [DEMO VIDEO](https://www.bilibili.com/video/BV1sA411P7wM/) ### [DEMO VIDEO](https://www.bilibili.com/video/BV17Q4y1B7mY/)
## 特性 ## 特性
🌍 **中文** 支持普通话并使用多种中文数据集进行测试：aidatatang_200zh, magicdata, aishell3， biaobei，MozillaCommonVoice 等 🌍 **中文** 支持普通话并使用多种中文数据集进行测试：aidatatang_200zh, magicdata, aishell3， biaobei，MozillaCommonVoice 等

2
README.md
View File

@ -16,7 +16,7 @@
🌍 **Webserver Ready** to serve your result with remote calling 🌍 **Webserver Ready** to serve your result with remote calling
### [DEMO VIDEO](https://www.bilibili.com/video/BV1sA411P7wM/) ### [DEMO VIDEO](https://www.bilibili.com/video/BV17Q4y1B7mY/)
## Quick Start ## Quick Start

15
synthesizer/hparams.py
View File

@ -49,12 +49,15 @@ hparams = HParams(
# frame that has all values < -3.4 # frame that has all values < -3.4
### Tacotron Training ### Tacotron Training
tts_schedule = [(2, 1e-3, 20_000, 24), # Progressive training schedule tts_schedule = [(2, 1e-3, 10_000, 12), # Progressive training schedule
(2, 5e-4, 40_000, 24), # (r, lr, step, batch_size) (2, 5e-4, 15_000, 12), # (r, lr, step, batch_size)
(2, 2e-4, 80_000, 24), # (2, 2e-4, 20_000, 12), # (r, lr, step, batch_size)
(2, 1e-4, 160_000, 24), # r = reduction factor (# of mel frames (2, 1e-4, 30_000, 12), #
(2, 3e-5, 320_000, 24), # synthesized for each decoder iteration) (2, 5e-5, 40_000, 12), #
(2, 1e-5, 640_000, 24)], # lr = learning rate (2, 1e-5, 60_000, 12), #
(2, 5e-6, 160_000, 12), # r = reduction factor (# of mel frames
(2, 3e-6, 320_000, 12), # synthesized for each decoder iteration)
(2, 1e-6, 640_000, 12)], # lr = learning rate
tts_clip_grad_norm = 1.0, # clips the gradient norm to prevent explosion - set to None if not needed tts_clip_grad_norm = 1.0, # clips the gradient norm to prevent explosion - set to None if not needed
tts_eval_interval = 500, # Number of steps between model evaluation (sample generation) tts_eval_interval = 500, # Number of steps between model evaluation (sample generation)