-
Is this normal? I looked at the code and there is audio splitting (great work btw) that looks like it can handle really large file lengths
-
# ❓ Questions & Help
안녕하세요?
컴퓨터 비전만 하다가 음성인식쪽은 처음인 음성ai어린이입니다.
혼자 음성인식 프로젝트를 맡아 정말 막막하여 이렇게나마 질문을 드립니다.
우선 TUNiB의 김수환님의 유튜브 영상을 보면서 openspeech에 알게되었고, 해당 프레임워크를 활용해서 STT 모델을 개발하려합니다.
제가 활용할 모델은…
-
Hi, I noticed there are some params here that are not in ctranslate2's implementation for [generate](https://opennmt.net/CTranslate2/python/ctranslate2.models.Whisper.html#ctranslate2.models.Whisper.g…
-
is it possible to cancel the recording so that it is not sent to openai and I do not get charged?
atm I only see start/stop
-
Phi3Transformer does not support an attention implementation through torch.nn.functional.scaled_dot_product_attention yet. Please request the support for this architecture: https://github.com/huggingf…
-
I am using a free ChatGPT account, have provided a new OpenAI API key, and set the Model to Chat 3.5 Turbo. As I am only using your extension and not running any other software which access ChatGPT, …
-
It's possible to fine-tune models to be able to use audio_ctx more freely, without affecting their knowledge too much.
Example with default settings (notice the ~3x speed difference):
```
$ ./mai…
-
Hi @speechbox developers,
I've been using the `ASRDiarizationPipeline` and noticed that there isn't a built-in option to specify the number of speakers when performing diarization. This feature wou…
-
I have a fine-tuned multi-lingual whisper model, which, when running purely using whisper (without whisper.cpp) outputs this:
> this is a ten second english test in order to check if it works well
…
-
# ComfyUI Error Report
## Error Details
- **Node Type:** ailab_OmniGen
- **Exception Type:** ValueError
- **Exception Message:** Phi3Transformer does not support an attention implementation throug…