-
### Describe the bug
Basically, in my local environment (Windows) I can download and use all models. Hovewer, when I build my project in docker, it fails to download the models with error:
```Trac…
-
HI, congrats on StyleTT2, would be great to setup a gradio demo for it on Hugging Face, you can see the guide to get started here: https://huggingface.co/docs/hub/spaces-sdks-gradio and here is a rece…
AK391 updated
11 months ago
-
### Describe the bug
Hello,
Today, when starting coqui-ai tss a new model is dowloaded
models/multilingual/multi-dataset/xtts_v2 is already downloaded however it has been changed. Redownloading…
-
Hi
Thank for this project and the documentation. It's not a issue but questions, idk if i can post here, sorry if not
I've succeeded to create a finetune model, but how do I select it? Do I have t…
-
### Describe the bug
Hello I just started playing with the TTS library and I am running tests using the TTS Command Line Interface (CLI).
I was able to try capacitron, vits (english and portuguese)…
240db updated
11 months ago
-
### Describe the bug
I use `TTS/recipes/ljspeech/xtts_v1/train_gpt_xtts.py` to fine-tune XTTSv1.1.2 model
Loading fine-tuned XTTS model will get an error
### To Reproduce
I use `train_gpt_x…
-
https://modrinth.com/resourcepack/mca-reborn-voice-pack
Previously, this voice pack matched the conversation of the villagers, but this update of the villagers' dialogue caused the language file and …
-
### Describe the bug
The updated version requires re-download of the checkpoints. However, they gives much worse voice cloning/synthesis than previous versions.
The same issue also mentioned in t…
-
Hi,
Does this repo also evaluate how realistic the voices are?
-
Hi,
Any idea on how to finetune an already existing tflite model (alexa for example) to increase the detection performace for a specific set of people ? The Colabs notebooks are great for a custom wa…