-
I just installed RealtimeSTT on windows.
I downloaded and installed cudnn and ffmpeg but they are just archives with binaries.
I didn't add anything to my PATH but the realtimestt_test.py seems…
-
Hi,
I found a rare condition, with a specific wav file, specific language and prompt, when I try to transcribe with word_timestamps=True, there is a list index out of range error in add_word_timesta…
-
I've got this issue while lunchning flask
(venv) PS C:\Users\Pierre\PycharmProjects\LLM-Minutes-of-Meeting> flask run
Loading Speech Model...
[2024-01-04 17:54:51.9…
-
I get the following error in docker logs when pushing the button or using the wakeword with the Atom Echo, and then nothing happens:
```
INFO:__main__:Ready
ERROR:asyncio:Task exception was never…
-
我已经从huggingface上下载了 BELLE-2/Belle-whisper-large-v3-zh-punct 和 Systran/faster-whisper-large-v3 两个模型。并按照配置文件的路径，放到了cache目录下。但是项目启动开始执行后，依然会再去下载模型。是放置本地模型的姿势哪里不对吗？路径命名有什么特别注意的吗？希望能得到解答
-
Install from manager, install manually, try fix, doesn't help
![2](https://github.com/user-attachments/assets/…
-
I played an episode in Turkish, and I didn't notice in the start, but after it finished generating, the subtitles were in Turkish, instead of English. The only change I did was change the model from "…
-
```
System Requirements:
CUDA version > 12.4
NVIDIA Driver version > 550
```
Since these are system requirements so it means it doesnt support AMD GPU's ? if yes then are there any plans to sup…
-
Error is:
```
ggml_metal_init: load pipeline error: Error Domain=AGXMetalA12 Code=3 "Encountered unlowered function call to air.simd_max.f32" UserInfo={NSLocalizedDescription=Encountered unlowered…
-
The title of the paper https://arxiv.org/pdf/2410.15608 is
> Moonshine: Speech Recognition for Live Transcription and Voice Commands
However, the model is a non-streaming model, could you describe…