-
Great work, thanks.
I successfully finetuned the 300M model with my own data. However, while using the latest streaming inference methods, specifies one female speaker to do long text speech synthe…
-
**Description**
I'm trying to deploy text to speech model with onnx and triton. When running the server, I get this error: failed:Protobuf parsing failed.
also model status is : UNAVAILABLE: Interna…
-
I am trying to use azure avatar with python.
It works fine in a basic mode, but fails in a chat mode.
After I have inputed some voice I see it on screen and I am getting:
```
Result id for avatar…
-
原模型输出结构:
![图片](https://github.com/user-attachments/assets/1572728b-d965-4bf3-8c19-aed8266f35c3)
onnx_edit后结构:
![图片](https://github.com/user-attachments/assets/b5a1d2f6-b71c-4fbe-b71b-9408291a0e49…
-
Hi,everyone:
I use a custom model. After executing start.sh and input audio, system will crash and return "No speech input detected" .
And I found some error logs in worker.log .
```
20…
-
**The code is encountering a ValueError when attempting to assign a voice for a speaker with the ID "speaker_01" and the SSML gender "M" (male). This indicates that the available voice pool does not c…
-
### Bug description
```
⚡ ~ litgpt finetune_lora meta-llama/Llama-3.2-1B --data JSON --data.json_path sanksrit-dataset.json --data.val_split_fraction 0.1 --train.epochs 1 --out_dir out/lla…
-
### Steps to reproduce:
1. Type "world, world, world" in MS Word.
2. NVDA+space switches to browse mode.
3. Ctrl+Home to the top of the document
4. NVDA+Ctrl+F opens the search dialog and enter "w…
-
**Describe the bug**
语音生成的效率太低了,同样的句子。openvoice 下只需要5秒,语音克隆也只要1分钟,而CosyVoice sft需要2分钟,zero-short更是需要5分钟以上
> 这是一段使用open voice 和 melo-tts生成的语音。 支持中文+英文的Cross-Lingual 句子。这个project真的挺challenging的,我们得赶…
-
# Compatibility Report
- Name of the game with compatibility issues: Tower!3D Pro
- Steam AppID of the game: 588190
## System Information
- GPU: RTX 3090ti
- Video driver version: 560.35.03
- …