fmax 8000,会对模型有什么影响吗
- Dominant language
- Python
- Stars
- 36.9k
- Forks
- 5.2k
- PR merge metrics
- No merged PRs in 30d
Description
想做小样本学习100样本左右,微调 tacotron 的 decoder 部分
#507
想知道fmax8000的话会对语音的相似度有什么影响吗,另外输出的这个 attention 图代表什么呢,横轴是步数,纵轴是attention,比如下面的这些输出该怎么分析呢,横轴代表步数的话为什么不是递增呢,这个图该怎么看呀
万分感谢!!希望可以深入交流
Contributor guide
No contributing guide indexed for this repository
Research direction
The issue mentions Tacotron decoder fine-tuning, fmax=8000, and attention plots, but identifies no repository files, tests, or entry points. Start by locating the Tacotron decoder and attention-visualization code, then compare the documented fmax behavior with the plotted outputs; done means providing a reproducible explanation supported by the relevant implementation or documentation.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- ai, audio-video-rtc, machine-learning
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 15/100