babysor / babysor/MockingBird

【求助】预训练后没有生成任何新数据

Open
#352 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

刚开始时是运行中有显示“页面文件太小”出错,但是在调整pagefile.sys之后,仍然没产生任何新文件。
前半段是这样的
F:\zhivoice\MockingBird-main>python pre.py F:/zhivoice -d aidatatang_200zh -n 6
Using data from:
F:\zhivoice\aidatatang_200zh\corpus\train
aidatatang_200zh: 0%| | 0/1 [00:00
preprocess_dataset(**vars(args))
File "F:\zhivoice\MockingBird-main\synthesizer\preprocess.py", line 88, in preprocess_dataset
print("Max input length (text chars): %d" % max(len(m[5]) for m in metadata))
ValueError: max() arg is an empty sequence

F:\zhivoice\MockingBird-main>
步骤都是按照教程一步步来的,恳请大佬指点一下,花了好长时间卡在这里实在没办法了

Contributor guide

No contributing guide indexed for this repository

Research direction

Start with pre.py and synthesizer/preprocess.py, using the reported `python pre.py F:/zhivoice -d aidatatang_200zh -n 6` command and the `aidatatang_200zh` training corpus. Trace why the run repeatedly reports `no wordS` and produces empty metadata before the `max()` call. Done means preprocessing recognizes the dataset and completes without the empty-sequence error.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.