Update app.py
Browse files
app.py
CHANGED
|
@@ -1,26 +1,15 @@
|
|
| 1 |
-
import os
|
| 2 |
-
os.system("python -m pip install --upgrade pip")
|
| 3 |
import openai
|
| 4 |
import gradio as gr
|
| 5 |
from gradio.components import Audio, Textbox
|
|
|
|
| 6 |
import re
|
| 7 |
import tiktoken
|
| 8 |
-
|
| 9 |
import whisper
|
|
|
|
| 10 |
from datetime import datetime, timezone, timedelta
|
| 11 |
import notion_df
|
| 12 |
import concurrent.futures
|
| 13 |
-
from IPython.core.display import HTML
|
| 14 |
-
os.system("pip install transformers>=4.0.0 pandas numpy spacy")
|
| 15 |
-
from transformers import GPT2Tokenizer
|
| 16 |
-
import pandas as pd
|
| 17 |
-
import numpy as np
|
| 18 |
-
import spacy
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
from spacy import displacy
|
| 22 |
-
|
| 23 |
-
nlp = spacy.load("en_core_web_sm")
|
| 24 |
|
| 25 |
# Define the tokenizer and model
|
| 26 |
tokenizer = GPT2Tokenizer.from_pretrained('gpt2-medium')
|
|
@@ -137,32 +126,14 @@ def transcribe(audio, text):
|
|
| 137 |
df = pd.DataFrame([chat_transcript])
|
| 138 |
notion_df.upload(df, 'https://www.notion.so/YENA-be569d0a40c940e7b6e0679318215790?pvs=4', title=str(published_date), api_key=API_KEY)
|
| 139 |
|
| 140 |
-
#
|
| 141 |
-
|
| 142 |
-
|
| 143 |
-
# Return the colorized chat transcript
|
| 144 |
-
return colorized_system_message
|
| 145 |
-
|
| 146 |
|
| 147 |
-
def colorize_text(text):
|
| 148 |
-
doc = nlp(text)
|
| 149 |
-
colorized_text = ""
|
| 150 |
-
|
| 151 |
-
for token in doc:
|
| 152 |
-
if token.ent_type_:
|
| 153 |
-
colorized_text += f'<span style="background-color: yellow;">{token.text_with_ws}</span>'
|
| 154 |
-
elif token.pos_ in {'NOUN'}:
|
| 155 |
-
colorized_text += f'<span style="color: blue;">{token.text_with_ws}</span>'
|
| 156 |
-
else:
|
| 157 |
-
colorized_text += token.text_with_ws
|
| 158 |
-
|
| 159 |
-
return colorized_text
|
| 160 |
-
|
| 161 |
-
|
| 162 |
# Define the input and output components for Gradio
|
| 163 |
audio_input = Audio(source="microphone", type="filepath", label="Record your message")
|
| 164 |
text_input = Textbox(label="Type your message", max_length=4096)
|
| 165 |
-
output_text =
|
|
|
|
| 166 |
|
| 167 |
# Define the Gradio interface
|
| 168 |
iface = gr.Interface(
|
|
@@ -177,4 +148,4 @@ iface = gr.Interface(
|
|
| 177 |
)
|
| 178 |
|
| 179 |
# Run the Gradio interface
|
| 180 |
-
iface.launch(
|
|
|
|
|
|
|
|
|
|
| 1 |
import openai
|
| 2 |
import gradio as gr
|
| 3 |
from gradio.components import Audio, Textbox
|
| 4 |
+
import os
|
| 5 |
import re
|
| 6 |
import tiktoken
|
| 7 |
+
from transformers import GPT2Tokenizer
|
| 8 |
import whisper
|
| 9 |
+
import pandas as pd
|
| 10 |
from datetime import datetime, timezone, timedelta
|
| 11 |
import notion_df
|
| 12 |
import concurrent.futures
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
|
| 14 |
# Define the tokenizer and model
|
| 15 |
tokenizer = GPT2Tokenizer.from_pretrained('gpt2-medium')
|
|
|
|
| 126 |
df = pd.DataFrame([chat_transcript])
|
| 127 |
notion_df.upload(df, 'https://www.notion.so/YENA-be569d0a40c940e7b6e0679318215790?pvs=4', title=str(published_date), api_key=API_KEY)
|
| 128 |
|
| 129 |
+
# Return the chat transcript
|
| 130 |
+
return system_message['content']
|
|
|
|
|
|
|
|
|
|
|
|
|
| 131 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 132 |
# Define the input and output components for Gradio
|
| 133 |
audio_input = Audio(source="microphone", type="filepath", label="Record your message")
|
| 134 |
text_input = Textbox(label="Type your message", max_length=4096)
|
| 135 |
+
output_text = gr.outputs.Textbox(label="Response")
|
| 136 |
+
output_audio = Audio()
|
| 137 |
|
| 138 |
# Define the Gradio interface
|
| 139 |
iface = gr.Interface(
|
|
|
|
| 148 |
)
|
| 149 |
|
| 150 |
# Run the Gradio interface
|
| 151 |
+
iface.launch()
|