babysor / babysor/MockingBird

模型替换成Tacotron2时,推理出现问题

Open
#797 2 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
36.9k
Forks
5.2k
PR merge metrics
No merged PRs in 30d

Description

当我输入一句带有逗号的句子,例如“欢迎使用工具箱,现已支持中文输入”时,我将句子处理成两个子句(与博主的处理方法一致),那么输入的batch就是2。但在Tacotron2里面,在判断gate门输出的时候,如果输入的句子batch为1时,就可以判断是否调出解码;但输入的句子batch为2时,就不能判断成功,我能将gate的阈值也变成batch为2的矩阵吗?

Contributor guide

No contributing guide indexed for this repository

Research direction

No files or tests are named. Start by tracing the Tacotron2 inference path that handles batched gate outputs, then reproduce the comma-separated input with batch sizes 1 and 2; done means decoding terminates correctly for both cases without breaking single-item inference.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.