Duplicate from aiotedu/aiotedu

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: Aiotedu
+emoji: 🐠
+colorFrom: green
+colorTo: indigo
+sdk: gradio
+sdk_version: 3.27.0
+app_file: app.py
+pinned: false
+duplicated_from: aiotedu/aiotedu
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,130 @@
+import numpy as np
+import gradio as gr
+# print("loading asr and tts success!")
+import soundfile
+import azure.cognitiveservices.speech as speechsdk
+import openai
+import os
+openai.api_key = os.environ.get("OPENAI_API_KEY")
+speech_key = os.environ.get("SPEECH_KEY")
+
+def ms_tts(text, filename):
+    speech_config = speechsdk.SpeechConfig(subscription=speech_key, region='eastus')
+    audio_config = speechsdk.audio.AudioOutputConfig(filename = filename)
+
+    # The language of the voice that speaks.
+    speech_config.speech_synthesis_voice_name='zh-CN-XiaochenNeural'
+
+    speech_synthesizer = speechsdk.SpeechSynthesizer(speech_config=speech_config, audio_config=audio_config)
+    
+    speech_synthesis_result = speech_synthesizer.speak_text_async(text).get()
+
+def ms_asr(filename):
+    # This example requires environment variables named "SPEECH_KEY" and "SPEECH_REGION"
+    speech_config = speechsdk.SpeechConfig(subscription=speech_key, region="eastus")
+    speech_config.speech_recognition_language="zh-CN"
+
+    audio_config = speechsdk.audio.AudioConfig(filename=filename)
+    speech_recognizer = speechsdk.SpeechRecognizer(speech_config=speech_config, audio_config=audio_config)
+
+    # print("Speak into your microphone.")
+    speech_recognition_result = speech_recognizer.recognize_once_async().get()
+
+    if speech_recognition_result.reason == speechsdk.ResultReason.RecognizedSpeech:
+        print("Recognized: {}".format(speech_recognition_result.text))
+    elif speech_recognition_result.reason == speechsdk.ResultReason.NoMatch:
+        print("No speech could be recognized: {}".format(speech_recognition_result.no_match_details))
+    elif speech_recognition_result.reason == speechsdk.ResultReason.Canceled:
+        cancellation_details = speech_recognition_result.cancellation_details
+        print("Speech Recognition canceled: {}".format(cancellation_details.reason))
+        if cancellation_details.reason == speechsdk.CancellationReason.Error:
+            print("Error details: {}".format(cancellation_details.error_details))
+            print("Did you set the speech resource key and region values?")
+            
+    return speech_recognition_result.text
+
+class Conversation:
+    def __init__(self, prompt, num_of_round):
+        self.prompt = prompt
+        self.num_of_round = num_of_round
+        self.messages = []
+        self.messages.append({"role": "system", "content": self.prompt})
+
+    def ask(self, question):
+        try:
+            self.messages.append( {"role": "user", "content": question})
+            response = openai.ChatCompletion.create(
+                model="gpt-3.5-turbo",
+                messages=self.messages,
+                temperature=0.5,
+                max_tokens=2048,
+                top_p=1,
+            )
+        except Exception as e:
+            print(e)
+            return e
+
+        message = response["choices"][0]["message"]["content"]
+        self.messages.append({"role": "assistant", "content": message})
+        
+        if len(self.messages) > self.num_of_round*2 + 1:
+            del self.messages[1:3]
+        return message
+    
+
+# prompt = """Say English"""
+prompt = """You are an conversation bot. You can speak English and Chinese. You were developed by the BOE AIOT CTO organization."""
+
+conv = Conversation(prompt, 5)
+
+def predict(input, history=[]):
+    history.append(input)
+    response = conv.ask(input)
+    history.append(response)
+    responses = [(u,b) for u,b in zip(history[::2], history[1::2])]
+    return response, responses, history
+
+def main(audio, history=[]):
+    
+    s,y = audio
+    
+    print(s)
+    assert s in [48000, 16000]
+    if s == 48000:  # Optional resample to 16000
+        y = (y / max(np.max(y), 1) * 32767)[::3].astype("int16")
+    soundfile.write("./input.wav",y,16000)
+
+    wav_res = ms_asr("./input.wav")
+    print("You said : ", wav_res)
+    # res = requests.post(url='http://10.10.239.164:8088',
+    # headers={"Content-Type": "application/json"},
+    # json={"prompt":wav_res,"history": historyList.hlist})
+
+    answer, his_list, history = predict(wav_res, history)
+
+    # print("answer: ", answer)
+    # print("history: ", history)
+    # if len(history)>=10:
+    #     historyList.hlist = history[1:]
+    # else:
+    #     historyList.hlist = history
+
+
+    ms_tts(text=answer, filename="./output.wav")
+    path1="./output.wav"
+    # print("historyList.hlist: ", historyList.hlist)
+    return his_list, history, path1
+
+
+with gr.Blocks() as demo:
+    state = gr.State([])
+    with gr.Row():
+        with gr.Column(scale=4):
+            txt = gr.Chatbot(label="ChatBox")
+            out_voice = gr.Audio(label="audio")
+        with gr.Column(scale=4):
+            mic = gr.Mic(label="input")
+            button = gr.Button("Generate")
+    button.click(main, [mic, state], [txt, state, out_voice])
+# demo.queue().launch(server_name = "0.0.0.0", server_port=8080)
+demo.queue().launch()

requirements.txt

@@ -0,0 +1,3 @@
+openai
+soundfile
+azure-cognitiveservices-speech