Spaces:
Running
Running
File size: 13,689 Bytes
43cd37c c5b0bb7 43cd37c c5b0bb7 43cd37c c5b0bb7 43cd37c c5b0bb7 43cd37c c5b0bb7 43cd37c c5b0bb7 43cd37c c5b0bb7 43cd37c c5b0bb7 43cd37c c5b0bb7 43cd37c c5b0bb7 43cd37c c5b0bb7 43cd37c c5b0bb7 43cd37c c5b0bb7 43cd37c c5b0bb7 43cd37c c5b0bb7 43cd37c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 |
# Audio_ingestion_tab.py
# Description: Gradio UI for ingesting audio files into the database
#
# Imports
import logging
#
# External Imports
import gradio as gr
#
# Local Imports
from App_Function_Libraries.Audio.Audio_Files import process_audio_files
from App_Function_Libraries.DB.DB_Manager import list_prompts
from App_Function_Libraries.Gradio_UI.Chat_ui import update_user_prompt
from App_Function_Libraries.Gradio_UI.Gradio_Shared import whisper_models
from App_Function_Libraries.Utils.Utils import cleanup_temp_files, default_api_endpoint, global_api_endpoints, \
format_api_name
# Import metrics logging
from App_Function_Libraries.Metrics.metrics_logger import log_counter, log_histogram
from App_Function_Libraries.Metrics.logger_config import logger
#
#######################################################################################################################
# Functions:
def create_audio_processing_tab():
with gr.TabItem("Audio File Transcription + Summarization", visible=True):
gr.Markdown("# Transcribe & Summarize Audio Files from URLs or Local Files!")
# Get and validate default value
try:
default_value = None
if default_api_endpoint:
if default_api_endpoint in global_api_endpoints:
default_value = format_api_name(default_api_endpoint)
else:
logging.warning(f"Default API endpoint '{default_api_endpoint}' not found in global_api_endpoints")
except Exception as e:
logging.error(f"Error setting default API endpoint: {str(e)}")
default_value = None
with gr.Row():
with gr.Column():
audio_url_input = gr.Textbox(label="Audio File URL(s)", placeholder="Enter the URL(s) of the audio file(s), one per line")
audio_file_input = gr.File(label="Upload Audio File", file_types=["audio/*"])
custom_title_input = gr.Textbox(label="Custom Title/Name", placeholder="Enter a custom title or name for the audio file")
use_cookies_input = gr.Checkbox(label="Use cookies for authenticated download", value=False)
cookies_input = gr.Textbox(
label="Audio Download Cookies",
placeholder="Paste your cookies here (JSON format)",
lines=3,
visible=False
)
use_cookies_input.change(
fn=lambda x: gr.update(visible=x),
inputs=[use_cookies_input],
outputs=[cookies_input]
)
diarize_input = gr.Checkbox(label="Enable Speaker Diarization", value=False)
whisper_model_input = gr.Dropdown(choices=whisper_models, value="medium", label="Whisper Model")
keep_timestamps_input = gr.Checkbox(label="Keep Timestamps", value=True)
with gr.Row():
custom_prompt_checkbox = gr.Checkbox(
label="Use a Custom Prompt",
value=False,
visible=True
)
preset_prompt_checkbox = gr.Checkbox(
label="Use a pre-set Prompt",
value=False,
visible=True
)
# Initialize state variables for pagination
current_page_state = gr.State(value=1)
total_pages_state = gr.State(value=1)
with gr.Row():
# Add pagination controls
preset_prompt = gr.Dropdown(
label="Select Preset Prompt",
choices=[],
visible=False
)
with gr.Row():
prev_page_button = gr.Button("Previous Page", visible=False)
page_display = gr.Markdown("Page 1 of X", visible=False)
next_page_button = gr.Button("Next Page", visible=False)
with gr.Row():
custom_prompt_input = gr.Textbox(
label="Custom Prompt",
placeholder="Enter custom prompt here",
lines=3,
visible=False
)
with gr.Row():
system_prompt_input = gr.Textbox(
label="System Prompt",
value="""<s>You are a bulleted notes specialist. [INST]```When creating comprehensive bulleted notes, you should follow these guidelines: Use multiple headings based on the referenced topics, not categories like quotes or terms. Headings should be surrounded by bold formatting and not be listed as bullet points themselves. Leave no space between headings and their corresponding list items underneath. Important terms within the content should be emphasized by setting them in bold font. Any text that ends with a colon should also be bolded. Before submitting your response, review the instructions, and make any corrections necessary to adhere to the specified format. Do not reference these instructions within the notes.``` \nBased on the content between backticks create comprehensive bulleted notes.[/INST]
**Bulleted Note Creation Guidelines**
**Headings**:
- Based on referenced topics, not categories like quotes or terms
- Surrounded by **bold** formatting
- Not listed as bullet points
- No space between headings and list items underneath
**Emphasis**:
- **Important terms** set in bold font
- **Text ending in a colon**: also bolded
**Review**:
- Ensure adherence to specified format
- Do not reference these instructions in your response.</s>[INST] {{ .Prompt }} [/INST]
""",
lines=3,
visible=False
)
custom_prompt_checkbox.change(
fn=lambda x: (gr.update(visible=x), gr.update(visible=x)),
inputs=[custom_prompt_checkbox],
outputs=[custom_prompt_input, system_prompt_input]
)
# Handle preset prompt checkbox change
def on_preset_prompt_checkbox_change(is_checked):
if is_checked:
prompts, total_pages, current_page = list_prompts(page=1, per_page=10)
page_display_text = f"Page {current_page} of {total_pages}"
return (
gr.update(visible=True, interactive=True, choices=prompts), # preset_prompt
gr.update(visible=True), # prev_page_button
gr.update(visible=True), # next_page_button
gr.update(value=page_display_text, visible=True), # page_display
current_page, # current_page_state
total_pages # total_pages_state
)
else:
return (
gr.update(visible=False, interactive=False), # preset_prompt
gr.update(visible=False), # prev_page_button
gr.update(visible=False), # next_page_button
gr.update(visible=False), # page_display
1, # current_page_state
1 # total_pages_state
)
preset_prompt_checkbox.change(
fn=on_preset_prompt_checkbox_change,
inputs=[preset_prompt_checkbox],
outputs=[preset_prompt, prev_page_button, next_page_button, page_display, current_page_state, total_pages_state]
)
# Pagination button functions
def on_prev_page_click(current_page, total_pages):
new_page = max(current_page - 1, 1)
prompts, total_pages, current_page = list_prompts(page=new_page, per_page=10)
page_display_text = f"Page {current_page} of {total_pages}"
return (
gr.update(choices=prompts),
gr.update(value=page_display_text),
current_page
)
prev_page_button.click(
fn=on_prev_page_click,
inputs=[current_page_state, total_pages_state],
outputs=[preset_prompt, page_display, current_page_state]
)
def on_next_page_click(current_page, total_pages):
new_page = min(current_page + 1, total_pages)
prompts, total_pages, current_page = list_prompts(page=new_page, per_page=10)
page_display_text = f"Page {current_page} of {total_pages}"
return (
gr.update(choices=prompts),
gr.update(value=page_display_text),
current_page
)
next_page_button.click(
fn=on_next_page_click,
inputs=[current_page_state, total_pages_state],
outputs=[preset_prompt, page_display, current_page_state]
)
# Update prompts when a preset is selected
def update_prompts(preset_name):
prompts = update_user_prompt(preset_name)
return (
gr.update(value=prompts["user_prompt"], visible=True),
gr.update(value=prompts["system_prompt"], visible=True)
)
preset_prompt.change(
update_prompts,
inputs=[preset_prompt],
outputs=[custom_prompt_input, system_prompt_input]
)
# Refactored API selection dropdown
api_name_input = gr.Dropdown(
choices=["None"] + [format_api_name(api) for api in global_api_endpoints],
value=default_value,
label="API for Summarization/Analysis (Optional)"
)
api_key_input = gr.Textbox(label="API Key (if required)", placeholder="Enter your API key here", type="password")
custom_keywords_input = gr.Textbox(label="Custom Keywords", placeholder="Enter custom keywords, comma-separated")
keep_original_input = gr.Checkbox(label="Keep original audio file", value=False)
chunking_options_checkbox = gr.Checkbox(label="Show Chunking Options", value=False)
with gr.Row(visible=False) as chunking_options_box:
gr.Markdown("### Chunking Options")
with gr.Column():
chunk_method = gr.Dropdown(choices=['words', 'sentences', 'paragraphs', 'tokens'], label="Chunking Method")
max_chunk_size = gr.Slider(minimum=100, maximum=1000, value=300, step=50, label="Max Chunk Size")
chunk_overlap = gr.Slider(minimum=0, maximum=100, value=0, step=10, label="Chunk Overlap")
use_adaptive_chunking = gr.Checkbox(label="Use Adaptive Chunking")
use_multi_level_chunking = gr.Checkbox(label="Use Multi-level Chunking")
chunk_language = gr.Dropdown(choices=['english', 'french', 'german', 'spanish'], label="Chunking Language")
chunking_options_checkbox.change(
fn=lambda x: gr.update(visible=x),
inputs=[chunking_options_checkbox],
outputs=[chunking_options_box]
)
process_audio_button = gr.Button("Process Audio File(s)")
with gr.Column():
audio_progress_output = gr.Textbox(label="Progress")
audio_transcription_output = gr.Textbox(label="Transcription")
audio_summary_output = gr.Textbox(label="Summary")
download_transcription = gr.File(label="Download All Transcriptions as JSON")
download_summary = gr.File(label="Download All Summaries as Text")
process_audio_button.click(
fn=process_audio_files,
inputs=[audio_url_input, audio_file_input, whisper_model_input, api_name_input, api_key_input,
use_cookies_input, cookies_input, keep_original_input, custom_keywords_input, custom_prompt_input,
chunk_method, max_chunk_size, chunk_overlap, use_adaptive_chunking, use_multi_level_chunking,
chunk_language, diarize_input, keep_timestamps_input, custom_title_input],
outputs=[audio_progress_output, audio_transcription_output, audio_summary_output]
)
def on_file_clear(file):
if file is None:
cleanup_temp_files()
audio_file_input.clear(
fn=on_file_clear,
inputs=[audio_file_input],
outputs=[]
)
#
# End of Audio_ingestion_tab.py
####################################################################################################################### |