-
```
What steps will reproduce the problem?
1. Go to a db
2. Click the question / answer
What is the expected output? What do you see instead?
Other than the first time, the TTS should be very fast to…
-
## Introduction
This RFC outlines the plan for implementing a new mobile view design from Figma into our React application. The design includes four main sections: Translation, Speech-to-Text (STT), …
-
I'm trying to use the code inside `text_to_speech_stream.ts` to get audio stream and upload it on aws s3 but it gives me below error.
```
/**
* Uses the ElevenLabs API to convert text to audio
…
-
-
I am running issue when generating audio.
Here's my code.
```python
%pip install ipython
from IPython.display import Audio, display
# Generate transcript only
from podcastfy.client import ge…
-
If you have, for example, a Korean road name, speech synthesis using `AVSpeechSynthesizer` skips straight over this.
I assume that this is fixable with better annotation of the voice instructions tex…
-
**出错信息**
 in loading state_dict for CLVP:
Missing key(s) in state_dict: "text_pos_emb.weight", "text_transformer.layers.layers.0.0.scale" ....
..... mismatch…
-
## 🐛 Bug
When importing anything from the main branch of Fairseq, an error occurs.
### To Reproduce
Install fresh Fairseq
```bash
pip install 'git+https://github.com/facebookresearch/fairs…