aishell3中的语音合成效果较差
- Dominant language
- Python
- Stars
- 36.9k
- Forks
- 5.2k
- PR merge metrics
- No merged PRs in 30d
Description
Preparing the encoder, the synthesizer and the vocoder...
Loaded encoder "pretrained.pt" trained to step 1594501
Synthesizer using device: cuda
Building hifigan
Loading 'vocoder/saved_models/pretrained/g_hifigan.pt'
Complete.
Removing weight norm...
Trainable Parameters: 0.000M
Loaded synthesizer "mandarin.pt" trained to step 75000
+----------+---+
| Tacotron | r |
+----------+---+
| 75k | 2 |
+----------+---+
Read ['江苏修鞋奶奶婉拒捐款一人养活患病老伴和儿子']
Synthesizing ['jiang1 su1 xiu1 xie2 nai3 nai3 wan3 ju4 juan1 kuan3 yi1 ren2 yang3 huo2 huan4 bing4 lao3 ban4 he2 er2 zi5']
| Generating 1/1
Done.
使用了百度网盘的合成器，请问是什么问题呢？
Contributor guide
No contributing guide indexed for this repository
Research direction
Start at the encoder, synthesizer, and vocoder initialization shown in the report, using pretrained.pt, mandarin.pt, and vocoder/saved_models/pretrained/g_hifigan.pt with the supplied AISHELL3 text. Compare the generated output with the expected synthesis quality and identify a reproducible cause and fix; no test or acceptance criteria are provided.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- audio-video-rtc, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100