-
Code：
```from RealtimeSTT import AudioToTextRecorder
import ssl
ssl._create_default_https_context = ssl._create_unverified_context
import torch
model, _ = torch.hub.load(repo_or_dir="snakers4…
-
Here I will post our benchmarks comparing these three instruments
-
**Which OS are you using?**
- OS: [e.g. iOS or Windows.. If you are using Google Colab, just Colab.]
windows 11
After a long-awaited update, I attempted to generate Chinese subtitles. As time …
-
I'm trying to run demo_part1.ipynb with default settings on win10 with python 3.9 through venv and get this error on 7th step:
7:
reference_speaker = 'resources/example_reference.mp3'
target_se, …
-
I encountered this error
`execution_frame.cc:857 VerifyOutputSizes] Expected shape from model of {1,-1,128} does not match actual shape of {1,1,128,6} for output If_0_then_branch__Inline_0__/Unsque…
-
I'm trying to use https://github.com/snakers4/silero-vad in candle, but what is the equivalent of the model() function it uses (like here: https://github.com/snakers4/silero-vad/blob/563106ef8cfac329c…
-
Doing VAD on the server makes up for a lot of unnecessary traffic and server load. Why not do it on the client?
Thanks to wasm, Silero VAD can be run entirely in the browser. I am building a simila…
-
Hi, thank you for the wonderful library.
Recently, [silero-vad v5](https://github.com/snakers4/silero-vad/releases/tag/v5.0) was released. Do you have any plans to support it in this library?
I t…
-
### Description
Introduce the capability to support ONNX subgraphs within the Burn framework, particularly for handling conditional inference computations. This feature aims to enable Burn to fully…
-
I'm trying to run the first demo but when I try running this command:
```
reference_speaker = 'resources/example_reference.mp3' # This is the voice you want to clone
target_se, audio_name = se_ext…