audio

.gitignore

@@ -150,3 +150,4 @@ request_llm/jittorllms
 multi-language
 request_llm/moss
 media
+flagged

config.py

@@ -60,7 +60,9 @@ CONCURRENT_COUNT = 100
 AUTO_CLEAR_TXT = False
 
 # 色彩主体，可选： "Default", "Green"
-THEME = "Green"
+THEME = "Default"
+
+ENABLE_AUDIO = True
 
 # 加一个live2d装饰
 ADD_WAIFU = False

crazy_functions/辅助面试.py

@@ -0,0 +1,45 @@
+from toolbox import update_ui
+from toolbox import CatchException, report_execption, write_results_to_file
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+import threading
+
+class InterviewAssistent():
+
+    def __init__(self):
+        pass
+
+    
+    # def audio_capture_thread(self):
+
+        # 第7步：所有线程同时开始执行任务函数
+        # handles = [ for index, fp in enumerate(file_manifest)]
+
+
+
+
+    def init(self):
+        self.captured_words = ""
+        # threading.Thread(target=self.audio_capture_thread, args=(self, 1))
+
+
+    def begin(self, llm_kwargs, plugin_kwargs, chatbot, history):
+        while True:
+            break
+            # yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+
+
+
+
+
+
+
+@CatchException
+def 辅助面试(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+    pass
+    # pip install -U openai-whisper
+    # while True:
+    #     time.sleep(4)
+    #     print(plugin_kwargs)
+    # ia = InterviewAssistent()
+    # yield from ia.begin(llm_kwargs, plugin_kwargs, chatbot, history)
+

main.py

@@ -6,8 +6,8 @@ def main():
     from request_llm.bridge_all import predict
     from toolbox import format_io, find_free_port, on_file_uploaded, on_report_generated, get_conf, ArgsGeneralWrapper, DummyWith
     # 建议您复制一个config_private.py放自己的秘密, 如API和代理网址, 避免不小心传github被别人看到
-    proxies, WEB_PORT, LLM_MODEL, CONCURRENT_COUNT, AUTHENTICATION, CHATBOT_HEIGHT, LAYOUT, API_KEY, AVAIL_LLM_MODELS, AUTO_CLEAR_TXT = \
+    proxies, WEB_PORT, LLM_MODEL, CONCURRENT_COUNT, AUTHENTICATION, CHATBOT_HEIGHT, LAYOUT, API_KEY, AVAIL_LLM_MODELS, AUTO_CLEAR_TXT, ENABLE_AUDIO = \
-        get_conf('proxies', 'WEB_PORT', 'LLM_MODEL', 'CONCURRENT_COUNT', 'AUTHENTICATION', 'CHATBOT_HEIGHT', 'LAYOUT', 'API_KEY', 'AVAIL_LLM_MODELS', 'AUTO_CLEAR_TXT')
+    get_conf('proxies', 'WEB_PORT', 'LLM_MODEL', 'CONCURRENT_COUNT', 'AUTHENTICATION', 'CHATBOT_HEIGHT', 'LAYOUT', 'API_KEY', 'AVAIL_LLM_MODELS', 'AUTO_CLEAR_TXT', 'ENABLE_AUDIO')
 
     # 如果WEB_PORT是-1, 则随机选取WEB端口
     PORT = find_free_port() if WEB_PORT <= 0 else WEB_PORT
@@ -57,6 +57,7 @@ def main():
         cookies = gr.State({'api_key': API_KEY, 'llm_model': LLM_MODEL})
         with gr_L1():
             with gr_L2(scale=2):
+                if ENABLE_AUDIO: audio = gr.Audio(source="microphone", streaming=True)
                 chatbot = gr.Chatbot(label=f"当前模型：{LLM_MODEL}")
                 chatbot.style(height=CHATBOT_HEIGHT)
                 history = gr.State([])
@@ -91,7 +92,7 @@ def main():
                         with gr.Accordion("更多函数插件", open=True):
                             dropdown_fn_list = [k for k in crazy_fns.keys() if not crazy_fns[k].get("AsButton", True)]
                             with gr.Row():
-                                dropdown = gr.Dropdown(dropdown_fn_list, value=r"打开插件列表", label="").style(container=False)
+                                dropdown = gr.Dropdown(dropdown_fn_list, value=r"打开插件列表", label="", show_label=False).style(container=False)
                             with gr.Row():
                                 plugin_advanced_arg = gr.Textbox(show_label=True, label="高级参数输入区", visible=False, 
                                                                  placeholder="这里是特殊函数插件的高级参数输入区").style(container=False)
@@ -133,6 +134,7 @@ def main():
         checkboxes.select(fn_area_visibility, [checkboxes], [area_basic_fn, area_crazy_fn, area_input_primary, area_input_secondary, txt, txt2, clearBtn, clearBtn2, plugin_advanced_arg] )
         # 整理反复出现的控件句柄组合
         input_combo = [cookies, max_length_sl, md_dropdown, txt, txt2, top_p, temperature, chatbot, history, system_prompt, plugin_advanced_arg]
+        if ENABLE_AUDIO: input_combo.append(audio)
         output_combo = [cookies, chatbot, history, status]
         predict_args = dict(fn=ArgsGeneralWrapper(predict), inputs=input_combo, outputs=output_combo)
         # 提交按钮、重置按钮
@@ -186,6 +188,8 @@ def main():
         stopBtn.click(fn=None, inputs=None, outputs=None, cancels=cancel_handles)
         stopBtn2.click(fn=None, inputs=None, outputs=None, cancels=cancel_handles)
 
+        demo.load()
+
     # gradio的inbrowser触发不太稳定，回滚代码到原始的浏览器打开函数
     def auto_opentab_delay():
         import threading, webbrowser, time

toolbox.py

@@ -40,6 +40,7 @@ def ArgsGeneralWrapper(f):
     """
     装饰器函数，用于重组输入参数，改变输入参数的顺序与结构。
     """
+    ENABLE_AUDIO, = get_conf('ENABLE_AUDIO')
     def decorated(cookies, max_length, llm_model, txt, txt2, top_p, temperature, chatbot, history, system_prompt, plugin_advanced_arg, *args):
         txt_passon = txt
         if txt == "" and txt2 != "": txt_passon = txt2
@@ -58,6 +59,7 @@ def ArgsGeneralWrapper(f):
         plugin_kwargs = {
             "advanced_arg": plugin_advanced_arg,
         }
+        if ENABLE_AUDIO: plugin_kwargs.update({'audio': args[0]})
         chatbot_with_cookie = ChatBotWithCookies(cookies)
         chatbot_with_cookie.write_list(chatbot)
         yield from f(txt_passon, llm_kwargs, plugin_kwargs, chatbot_with_cookie, history, system_prompt, *args)