TomRidder

Results 55 issues of TomRidder

ERROR: Cannot install -r requirements.txt (line 26), demucs and whisperx because these package versions have conflicting dependencies. The conflict is caused by: demucs 4.1.0a3 depends on torchaudio=0.8 whisperx 3.3.0 depends...

chatbot | [INFO][2025-01-27 07:52:34,700][local_storage_impl.py:17] => Load LocalStorage Success chatbot | Traceback (most recent call last): chatbot | File "/app/apps/chatbot/process/process.py", line 53, in chat chatbot | short_history = singleton_sys_config.memory_storage_driver.search_short_memory( chatbot |...

def llm_response(message,nerfreal:BaseReal): start = time.perf_counter() from openai import OpenAI client = OpenAI( # 如果您没有配置环境变量,请在此处用您的API Key进行替换 api_key="sk-krJFkFO5gfJDex11BHLn5nl5e95QRtA4nRz9jScZ8duJdKuU", base_url="https://yunwu.ai/", ================================== INFO:logger:------actual avg final fps:31.5440 INFO:logger:llm Time init: 0.6586887999992541s INFO:logger:llm Time to last...

当 batch/input 里面的文件数量多于 task_setting 里面的 就会报错 Warning: Files in input folder not mentioned in Excel sheet

Loading model... 🎵 Separating audio... ┌─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┐ │ Error in step '🎙️ Transcribing with Whisper': │ │ data. DefaultCPUAllocator: not enough memory: you tried to allocate 12845161792 bytes ============================================================== 在后台分离音频的时候遇到了DefaultCPUAllocator 有没有办法把这一步交给gpu来做