Spaces:
Runtime error
Runtime error
Commit
·
77070f9
1
Parent(s):
1c1c8cf
minor fixes
Browse files- diarization.py +3 -3
- file_name.py +8 -3
- utils.py +16 -16
diarization.py
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
from pyannote.audio import Pipeline
|
2 |
from pydub import AudioSegment
|
3 |
-
import
|
4 |
import torch
|
5 |
import json
|
6 |
import gc
|
@@ -52,7 +52,7 @@ def audio_segmentation(input_file, speaker_groups_dict):
|
|
52 |
|
53 |
|
54 |
def save_groups_json(sample_groups_list: list, speaker_groups_dict: dict):
|
55 |
-
with open(
|
56 |
json.dump(sample_groups_list, json_file_sample)
|
57 |
-
with open(
|
58 |
json.dump(speaker_groups_dict, json_file_speaker)
|
|
|
1 |
from pyannote.audio import Pipeline
|
2 |
from pydub import AudioSegment
|
3 |
+
from file_name import *
|
4 |
import torch
|
5 |
import json
|
6 |
import gc
|
|
|
52 |
|
53 |
|
54 |
def save_groups_json(sample_groups_list: list, speaker_groups_dict: dict):
|
55 |
+
with open(get_sample_groups_json(), "w", encoding="utf-8") as json_file_sample:
|
56 |
json.dump(sample_groups_list, json_file_sample)
|
57 |
+
with open(get_speaker_groups_json(), "w", encoding="utf-8") as json_file_speaker:
|
58 |
json.dump(speaker_groups_dict, json_file_speaker)
|
file_name.py
CHANGED
@@ -34,8 +34,13 @@ def get_video_subtitle_file():
|
|
34 |
return f"{current_working_directory}/output_{get_title()}.mp4"
|
35 |
|
36 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
37 |
start_time_for_adjustment = "00:00:00"
|
38 |
end_time_for_adjustment = "01:00:00"
|
39 |
-
|
40 |
-
sample_groups_json = "sample_groups.json"
|
41 |
-
speaker_groups_json = "speaker_groups.json"
|
|
|
34 |
return f"{current_working_directory}/output_{get_title()}.mp4"
|
35 |
|
36 |
|
37 |
+
def get_sample_groups_json():
|
38 |
+
return f"{current_working_directory}/sample_groups_{get_title()}.json"
|
39 |
+
|
40 |
+
|
41 |
+
def get_speaker_groups_json():
|
42 |
+
return f"{current_working_directory}/speaker_groups_{get_title()}.json"
|
43 |
+
|
44 |
+
|
45 |
start_time_for_adjustment = "00:00:00"
|
46 |
end_time_for_adjustment = "01:00:00"
|
|
|
|
|
|
utils.py
CHANGED
@@ -4,14 +4,14 @@ import os
|
|
4 |
|
5 |
|
6 |
def load_groups_json():
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
return sample_groups_list, speaker_groups_dict
|
16 |
|
17 |
|
@@ -35,12 +35,12 @@ def read_transcribe_subtitle_file(adjustment: bool):
|
|
35 |
transcribe = get_transcribe_adjusted_file()
|
36 |
subtitle = get_subtitle_adjusted_file()
|
37 |
|
38 |
-
|
39 |
-
|
40 |
-
|
41 |
-
|
42 |
-
|
43 |
-
|
44 |
-
|
45 |
-
|
46 |
return transcribe_txt_list, subtitle_txt_list
|
|
|
4 |
|
5 |
|
6 |
def load_groups_json():
|
7 |
+
if not os.path.exists(get_sample_groups_json()) or not os.path.exists(get_speaker_groups_json()):
|
8 |
+
print("JSON file doesn't exist")
|
9 |
+
return [], {}
|
10 |
+
|
11 |
+
with open(get_sample_groups_json(), "r", encoding="utf-8") as json_file_sample:
|
12 |
+
sample_groups_list: list = json.load(json_file_sample)
|
13 |
+
with open(get_speaker_groups_json(), "r", encoding="utf-8") as json_file_speaker:
|
14 |
+
speaker_groups_dict: dict = json.load(json_file_speaker)
|
15 |
return sample_groups_list, speaker_groups_dict
|
16 |
|
17 |
|
|
|
35 |
transcribe = get_transcribe_adjusted_file()
|
36 |
subtitle = get_subtitle_adjusted_file()
|
37 |
|
38 |
+
if not os.path.exists(transcribe) or not os.path.exists(subtitle):
|
39 |
+
print("Transcribe or subtitle file doesn't exist")
|
40 |
+
return [], []
|
41 |
+
|
42 |
+
with open(transcribe, "r", encoding="utf-8") as file:
|
43 |
+
transcribe_txt_list = file.readlines()
|
44 |
+
with open(subtitle, "r", encoding="utf-8") as file:
|
45 |
+
subtitle_txt_list = file.readlines()
|
46 |
return transcribe_txt_list, subtitle_txt_list
|