Duplicate from hwberry2/WhisperDemo

Co-authored-by: Bill Berry <hwberry2@users.noreply.huggingface.co>

.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: WhisperDemo
+emoji: 🌖
+colorFrom: blue
+colorTo: gray
+sdk: gradio
+sdk_version: 3.20.0
+app_file: app.py
+pinned: false
+duplicated_from: hwberry2/WhisperDemo
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,115 @@
+import os
+import gradio as gr
+import openai
+from gtts import gTTS # Google Text To Speech
+
+# load the api key
+openai.api_key = os.environ["OPEN_AI_KEY"]
+
+# takes an audio file from the microphone
+# submits the raw audio to OpenAI for 
+# Speech to Text Translation
+# input from Microphone Component
+# output to User Input - Textbox Component
+def transcribe(audio):   
+        audio_file = open(audio, "rb")    
+        # Call the transcribe method with the file-like object
+        transcript = openai.Audio.transcribe("whisper-1", audio_file)
+        
+        return transcript["text"]
+
+
+
+# Create a Gradio App using Blocks    
+with gr.Blocks() as demo:
+    gr.Markdown(
+    """
+    # Welcome to the Virtual Therapist Chat Bot!
+    """
+    )
+    with gr.Accordion("Click for Instructions:"):
+            gr.Markdown(
+    """
+    * Tell the therapist your problems, by recording your query.
+    * Submit your query, and follow the chat or listen to the Therapists advice.
+    * When you are ready to respond, clear your last recording and resubmit.
+    note: Transcribe Audio does not work on iOS
+    """)
+        
+    
+    # First message as instructions to OpenAI
+    # Establishes a State object to create a
+    # unique state for each user and on reload
+    messages = gr.State(value=[{"role": "system", "content": "You are a therapist. Respond in less than 5 sentences."}])
+
+    # Takes the users transcribed audio as a string
+    # Takes the messages list as a reference
+    # Sends the ongoing chat log to OpenAI
+    # input from User Input - Textbox Component
+    # output to Chat Log - Textbox Component
+    def botResponse(user_input, messages):
+        # adds the user input to the ongoing chat log
+        # and submits the log to OpenAI
+        messages.append({"role": "user", "content": user_input})
+        response = openai.ChatCompletion.create(
+          model="gpt-3.5-turbo-0301",
+          messages=messages
+        )
+
+        # Parse the response from OpenAI and store
+        # it in the chat log
+        system_message = response["choices"][0]["message"]["content"]
+        messages.append({"role": "assistant", "content": system_message})
+
+        # Process the messages list to get the
+        # chat log into a string. Exclude the
+        # System responses from the string
+        chat_transcript = ""
+        for message in messages:
+            if (message["role"] != "system"):
+                chat_transcript += message["role"] + ": " + message["content"] + "\n\n"
+    
+        return chat_transcript
+
+    # Gets the last message in the 
+    # chat log and uses GTTS to
+    # convert the last response into
+    # an audio file. Returns a path to
+    # the converted text as an mp3 file
+    # input from messages as a reference
+    # output to GPT Voice - Audio Component
+    def giveVoice(messages):
+        bot_message=messages[-1]
+        
+        myobj = gTTS(text=bot_message["content"])
+        myobj.save("temp.mp3")
+    
+        dir = os.getcwd()
+        new_path = os.path.join(dir, "temp.mp3")
+    
+        return new_path
+
+    # Creates the Gradio interface objects
+    # The submit button triggers a cascade of
+    # events that each engage a different 
+    # component as input/output
+    with gr.Row():
+        with gr.Column(scale=1):
+            user_audio = gr.Audio(source="microphone", type="filepath", label="Input Phrase")
+            submit_btn = gr.Button(value="Transcribe Audio")
+            submit_btn2 = gr.Button(value="Submit Text")
+            gpt_voice = gr.Audio(label="Therapists Advice")
+        with gr.Column(scale=2):
+            user_transcript = gr.Text(label="Audio Translation", interactive=False)
+            user_text = gr.Text(label="Text Input")
+            gpt_transcript = gr.Text(label="Chat Transcript")
+    submit_btn.click(transcribe, user_audio, user_transcript)
+    submit_btn2.click(botResponse, [user_text, messages], gpt_transcript)
+    user_transcript.change(botResponse, [user_transcript, messages], gpt_transcript)
+    gpt_transcript.change(giveVoice, messages, gpt_voice)
+    
+    
+# creates a local web server
+# if share=True creates a public
+# demo on huggingface.co
+demo.launch(share=False)

requirements.txt

@@ -0,0 +1,2 @@
+openai
+gtts