Sujeendran Menon

Hi, I am trying to port this model to OpenVINO IR. But I will need to know few details about the model: 1. Input and output nodes 2. Shape of...

Hi, Is there a factory reset functionality using CONFIG_BOOTLOADER_APP_ROLLBACK_ENABLE option within this library? It would be good addition. I work with PlatformIO and am not sure how this option can...

Inference speed comparison

1

Hi! Could you share some details about the inference speed compared to Griffin-Lim/WaveNet/WaveRNN?

Loss calculation

1

Hi! Can you help me understand how is the loss calculated and what is the expected good loss value from training the model?

Null safety update

3

Hi, Are you guys planning to update this example for null safety?

Hi, I am currently using ReSpeaker 4 Mic hat which is manually configured. I want to use DOA features of respeaker and have been trying to make the audio-server listen...

RuntimeError: Expected object of backend CPU but got backend CUDA for argument

18

Hi, Which version of PyTorch , CUDA and cuDNN do you use? I always run into this error. My setup: Windows 10 Pro python 3.6.5 torch 1.1.0 Cuda 10.0 cuDNN...

This change allows CUDA 11.8 users to use ctransformers with GPU support. #90 #170 #139

Last code generated never used for prompt generation

2

### System Info OS version: Windows 10 Python version: 3.10 PandasAI version: 2.0.40 ### 🐛 Describe the bug https://github.com/Sinaptik-AI/pandas-ai/blob/64e6dcd8cbded4228eb1fc9382df71e80ccd9c1e/pandasai/pipelines/chat/prompt_generation.py#L64 While using this library I noticed this last_code_generated is always None...

Hi, I have been trying out this workflow in replicate and comfy-ui and found the results to be pretty good. Only problem I see is that when pattern is enabled,...