Spaces:
Runtime error
Runtime error
File size: 10,268 Bytes
0baca95 3b04551 0baca95 3b04551 f95be78 7c1d20a c6bdfa8 0baca95 607f1ae 1cc7035 a5f5c9f 3b04551 92791f8 0baca95 92791f8 03e603a 0baca95 365609b 7d21ed5 29d8a43 90f97b8 0baca95 0c1bb10 3b5ec49 1cc7035 3b5ec49 1cc7035 3b5ec49 1cc7035 3b5ec49 1cc7035 3b5ec49 1cc7035 bf32acd 3b5ec49 20c4b17 1cc7035 3b5ec49 1cc7035 3b5ec49 0baca95 f1ff944 0baca95 f1ff944 0baca95 3b04551 0baca95 fdcc758 3b04551 0baca95 3b04551 0baca95 3b04551 0baca95 c6bdfa8 0baca95 0c1bb10 043c163 fdcc758 4176bf3 0baca95 4176bf3 0baca95 2672b0d 607f1ae 58f8d16 3b5ec49 cfa894e 725e29e 90f97b8 3b5ec49 a0772af eabc593 d555084 eabc593 a0772af 1cc7035 eabc593 90f97b8 a0772af 607f1ae dec2550 0baca95 2936031 0baca95 3b04551 0baca95 3b04551 0baca95 3b04551 0baca95 3b04551 0baca95 3b04551 607f1ae cfa894e 607f1ae 3b04551 2672b0d cfa894e dec2550 cfa894e 0fb5151 cfa894e 0baca95 cfa894e 0fb5151 2672b0d cfa894e 5622cb6 cfa894e f1ff944 cfa894e 46e0397 5622cb6 46e0397 cfa894e f1ff944 cfa894e ff28df8 0baca95 0fb5151 2672b0d 0baca95 6468b0f 0baca95 2672b0d 0baca95 d4349ec f1ff944 6468b0f 0baca95 2672b0d 0baca95 3b04551 415e92e 0baca95 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 |
from huggingface_hub import hf_hub_download
import os
import time
import gradio as gr
import yt_dlp
import sys
import uuid
import traceback
import tensorflow
import csv
import json
embed_html1 = '<iframe width="560" height="315" src="https://www.youtube.com/embed/'
embed_html2 = '" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>'
# NO GPU ?
os.environ['CUDA_VISIBLE_DEVICES'] = '-1'
os.environ["TF_CPP_MIN_LOG_LEVEL"] = "3"
# tensorflow.config.threading.set_intra_op_parallelism_threads(8)
# tensorflow.config.threading.set_inter_op_parallelism_threads(8)
#print(f"Available GPUs {tensorflow.config.list_physical_devices('GPU')}")
#
python_path = hf_hub_download(
repo_id=os.environ["REPO_ID"],
repo_type="space",
filename=os.environ["MODEL_FILE"],
use_auth_token=os.environ["TOKEN"],
)
# print("PATH : ", python_path)
sys.path.append(os.environ["PRIVATE_DIR"])
from models import *
max_results = 100
max_output = 50
# global (faster)
ind = get_index()
ind_filenames = get_audio_names()
catalog = get_catalog()
url_dict = get_durl_myma()
dict_catalog = get_dict_catalog()
fixation_id_to_file_name = {}
for file_name, infos in dict_catalog.items():
# we want only main versions
if infos["Parent fixation id"].strip():
continue
fixation_id_to_file_name[infos["Fixation id"].strip()] = file_name
child_to_parent_filename = {}
count = count_failed = 0
for file_name, infos in dict_catalog.items():
if not infos["Parent fixation id"].strip():
continue
count += 1
try:
child_to_parent_filename[file_name] = fixation_id_to_file_name[
infos["Parent fixation id"].strip()
]
except Exception as e:
print(f"No parent for {file_name} : {e}")
count_failed += 1
print(f"{count_failed} tracks have no parent / {count} tracks")
parent_file_names = set(list(fixation_id_to_file_name.values()))
file_name_to_url = {}
for file_url in url_dict.values():
file_name = os.path.splitext(os.path.basename(file_url))[0]
if file_name not in parent_file_names:
continue
file_name_to_url[file_name] = file_url
parent_file_names = []
fixation_id_to_file_name = []
with open("fixation_id_to_file_name.json", "w") as w, open(
"child_to_parent_filename.json", "w"
) as w2, open("file_name_to_url.json", "w") as w3:
json.dump(fixation_id_to_file_name, w)
json.dump(child_to_parent_filename, w2)
json.dump(file_name_to_url, w3)
parent_file_names = []
fixation_id_to_file_name = {}
def download_audio(id_video):
id = id_video.split("?v=")[-1][:11]
file_name = f"youtube_video_{id}.mp3"
with yt_dlp.YoutubeDL(
{"extract_audio": True, "format": "bestaudio", "outtmpl": file_name}
) as video:
video.download(id_video)
embed_html_all = embed_html1 + id + embed_html2
return file_name, embed_html_all
def process_url(input_path):
# setup the client
# try :
file_name, embed_html_all = download_audio(input_path)
return process(file_name, embed_html_all)
# except:
# return "", "Erreur Input", "", "Erreur Input", "", "Erreur Input", "", "Erreur Input", "", "Erreur Input", "", "Erreur Input", "", "Erreur Input", "", "Erreur Input", "", "Erreur Input", "", "Erreur Input", ""
def process_file(input_path):
return process(input_path, "")[1:]
def process(file_name, embed_html_all):
"""try :"""
emb, _ = get_embed(file_name)
try:
os.remove(file_name)
except:
print(traceback.format_exc())
# => global
timestart = time.time()
D, I = do_search(emb, ind)
print("search time :", time.time() - timestart)
print("DEBUG DISTANCES : ", D)
tops = get_topN(I, ind_filenames, url_dict, catalog, max_results)
formated = [{"f": "Choose a result to play", "t": ""}]
output_csv = f"{file_name}_results.csv"
with open(output_csv, "w") as w:
writer = csv.writer(w)
header = False
already = set()
for position, top in enumerate(tops):
if len(formated) / 2 >= max_output:
break
file = os.path.splitext(os.path.basename(top))[0]
try:
file = child_to_parent_filename[file]
top = file_name_to_url[file]
except KeyError:
pass
if file in already:
continue
already.add(file)
file_name = file
if file in dict_catalog:
if not header:
writer.writerow(list(dict_catalog[file].keys()))
header = True
writer.writerow(dict_catalog[file].values())
file_name = dict_catalog[file]["Track name"]
try:
file_name += " - " + dict_catalog[file]["Composer1 full name"]
except:
pass
try:
file_name += " - " + dict_catalog[file]["Album name"]
except:
pass
else:
writer.writerow([file, "no metadata provided"])
formated.append({"f": f"{position+1} - {file_name}", "t": top})
return (embed_html_all, output_csv, formated)
"""except:
return embed_html_all, "Erreur Input", "", "Erreur Input", "", "Erreur Input", "", "Erreur Input", "", "Erreur Input", "", "Erreur Input", "", "Erreur Input", "", "Erreur Input", "", "Erreur Input", "", "Erreur Input", ""
"""
with gr.Blocks() as demo:
with gr.Row():
with gr.Column():
with gr.Row():
# gr.HTML(embed_html)
html = gr.HTML()
with gr.Row():
with gr.Column():
audio_url_input = gr.Textbox(
placeholder="YouTube video URL", label="YouTube video URL"
)
analyze_url_btn = gr.Button("Search from URL")
with gr.Row():
with gr.Column():
audio_input_file = gr.Audio(type="filepath", label="Audio Input")
analyze_file_btn = gr.Button("Search from file")
with gr.Row():
with gr.Column():
csv_results = gr.File(label="Results as CSV")
with gr.Row():
with gr.Column():
results = gr.JSON(visible=False)
select_results = gr.Dropdown(label="Results", choices=[])
audio_player = gr.Audio(None, label="Results player")
@select_results.select(inputs=select_results, outputs=audio_player)
def change_audio(value):
if value:
return gr.Audio(value, label="Results player")
return gr.Audio(None, label="Results player")
@results.change(
inputs=results,
outputs=select_results,
)
def update_select(json_results):
try:
print("change dropdown")
return gr.Dropdown(
label="Results",
choices=[(k["f"], k["t"]) for k in json_results],
value=None,
)
except:
return gr.Dropdown(
choices=[],
label="Results",
)
@audio_input_file.change(
outputs=[
audio_url_input,
results,
select_results,
csv_results,
audio_player,
html,
]
)
def cleanup_on_file():
print("cleanup on file change")
return (
gr.Textbox(
placeholder="YouTube video URL", label="YouTube video URL"
),
gr.JSON([{"f": "Choose a result to play", "t": ""}], visible=False),
gr.Dropdown(label="Results", choices=[]),
gr.File(None, label="Results as CSV"),
gr.Audio(None, label="Results player"),
gr.HTML(""),
)
@audio_url_input.change(
outputs=[
audio_input_file,
results,
select_results,
csv_results,
audio_player,
html,
]
)
def cleanup_on_url():
print("cleanup on url change")
return (
gr.Audio(None, type="filepath", label="Audio Input"),
gr.JSON([{"f": "Choose a result to play", "t": ""}], visible=False),
gr.Dropdown(choices=[], label="Results"),
gr.File(None, label="Results as CSV"),
gr.Audio(None, label="Results player"),
gr.HTML(""),
)
analyze_url_btn.click(
process_url,
inputs=[audio_url_input],
outputs=[html, csv_results, results],
)
gr.Examples(
examples=[
"https://www.youtube.com/watch?v=aNzCDt2eidg",
"https://www.youtube.com/watch?v=NBE-uBgtINg",
"https://www.youtube.com/watch?v=5NV6Rdv1a3I",
"https://www.youtube.com/watch?v=OiC1rgCPmUQ", #
"https://www.youtube.com/watch?v=dRX0wDNK6S4", #
"https://www.youtube.com/watch?v=Guzu9aAeDIc",
],
inputs=[audio_url_input],
outputs=[html, csv_results, results],
fn=process_url,
cache_examples=False,
examples_per_page=20,
run_on_click=True,
)
analyze_file_btn.click(
process_file,
inputs=[audio_input_file],
outputs=[csv_results, results],
)
demo.launch(debug=False)
|