-
We need to replace the current fishspeech with better TTS model.
WIP Shortlist of Possible candidates:
- Amphion (https://github.com/open-mmlab/Amphion)
-
### Describe the bug
```
raise ClientConnectorCertificateError(req.connection_key, exc) from exc
aiohttp.client_exceptions.ClientConnectorCertificateError: Cannot connect to host github.com:443…
-
### Describe the bug
After updating packages and external modules, I suddenly could no longer start the project with this error:
```
* Running on local URL: http://0.0.0.0:7770
Traceback (mos…
-
Description:
I converted the decoder of a TTS model (with HiFi-GAN vocoder) from PyTorch to ONNX and then to an engine format. During inference, both input and output shapes are dynamic, changing wit…
-
In your quick use manual (MeloTTS/docs/quick_use.md) you mention the following TTS models:
German
- [sanfte Männerstimme](https://app.myshell.ai/widget/JFnAn2)
- [sanfte Frauenstimme](https://app…
-
Having a really hard time getting the Elevenlabs voice TTS to work with a dedicated/cloned voice. I'm using the voice-pipeline-agent-python example. It does work with the standard openai.TTS voice.
…
-
test: **Add with torch_npu.npu.profile(profiler_result_path="./result",use_e2e_profiler=True): to get the profile data**
```
import torch
import torch_npu
from melo.api import TTS
import time
fr…
vfdff updated
1 month ago
-
### 🚀 The feature, motivation and pitch
"To adapt to the TTS task, I need to perform embedding mapping outside the model and insert the speaker embedding, then pass the embedding with speaker informa…
-
### Describe the bug
Code:
```_t1.py
from TTS.api import TTS
tts = TTS(model_name="voice_conversion_models/multilingual/vctk/freevc24", progress_bar=False).to("cuda:2")
tts.voice_conversion_to_…
-
@ROBERT-MCDOWELL
I don't know if you'll find this helpful or not but Ive managed to get all [Coqui tts](https://github.com/coqui-ai/TTS), [piper-tts](https://github.com/rhasspy/piper) and [stylett…