Spaces:
Sleeping
Sleeping
ChiBenevisamPas
commited on
Commit
•
0dbfe10
1
Parent(s):
3d2a173
Remove TS
Browse files
app.py
CHANGED
@@ -82,45 +82,39 @@ def embed_hardsub_in_video(video_file, srt_file, output_video):
|
|
82 |
raise RuntimeError(f"Error running ffmpeg: {e}")
|
83 |
|
84 |
def write_word(transcription, output_file, tokenizer=None, translation_model=None):
|
85 |
-
"""Creates a Word document from the transcription."""
|
86 |
doc = Document()
|
87 |
for i, segment in enumerate(transcription['segments']):
|
88 |
-
start = segment['start']
|
89 |
-
end = segment['end']
|
90 |
text = segment['text']
|
91 |
|
92 |
if translation_model:
|
93 |
text = translate_text(text, tokenizer, translation_model)
|
94 |
|
95 |
-
doc.add_paragraph(f"{i + 1}.
|
96 |
doc.save(output_file)
|
97 |
|
98 |
def write_pdf(transcription, output_file, tokenizer=None, translation_model=None):
|
99 |
-
"""Creates a PDF document from the transcription."""
|
100 |
pdf = FPDF()
|
101 |
pdf.set_auto_page_break(auto=True, margin=15)
|
102 |
pdf.add_page()
|
103 |
pdf.set_font("Arial", size=12)
|
104 |
|
105 |
for i, segment in enumerate(transcription['segments']):
|
106 |
-
start = segment['start']
|
107 |
-
end = segment['end']
|
108 |
text = segment['text']
|
109 |
|
110 |
if translation_model:
|
111 |
text = translate_text(text, tokenizer, translation_model)
|
112 |
|
113 |
-
pdf.multi_cell(0, 10, f"{i + 1}.
|
114 |
|
115 |
pdf.output(output_file)
|
116 |
|
117 |
def write_ppt(transcription, output_file, tokenizer=None, translation_model=None):
|
118 |
-
"""Creates a PowerPoint presentation from the transcription."""
|
119 |
ppt = Presentation()
|
120 |
|
121 |
for i, segment in enumerate(transcription['segments']):
|
122 |
-
start = segment['start']
|
123 |
-
end = segment['end']
|
124 |
text = segment['text']
|
125 |
|
126 |
if translation_model:
|
@@ -128,7 +122,7 @@ def write_ppt(transcription, output_file, tokenizer=None, translation_model=None
|
|
128 |
|
129 |
slide = ppt.slides.add_slide(ppt.slide_layouts[5]) # Blank slide
|
130 |
title = slide.shapes.title
|
131 |
-
title.text = f"{i + 1}.
|
132 |
|
133 |
ppt.save(output_file)
|
134 |
|
|
|
82 |
raise RuntimeError(f"Error running ffmpeg: {e}")
|
83 |
|
84 |
def write_word(transcription, output_file, tokenizer=None, translation_model=None):
|
85 |
+
"""Creates a Word document from the transcription without timestamps."""
|
86 |
doc = Document()
|
87 |
for i, segment in enumerate(transcription['segments']):
|
|
|
|
|
88 |
text = segment['text']
|
89 |
|
90 |
if translation_model:
|
91 |
text = translate_text(text, tokenizer, translation_model)
|
92 |
|
93 |
+
doc.add_paragraph(f"{i + 1}. {text.strip()}") # No timestamps
|
94 |
doc.save(output_file)
|
95 |
|
96 |
def write_pdf(transcription, output_file, tokenizer=None, translation_model=None):
|
97 |
+
"""Creates a PDF document from the transcription without timestamps."""
|
98 |
pdf = FPDF()
|
99 |
pdf.set_auto_page_break(auto=True, margin=15)
|
100 |
pdf.add_page()
|
101 |
pdf.set_font("Arial", size=12)
|
102 |
|
103 |
for i, segment in enumerate(transcription['segments']):
|
|
|
|
|
104 |
text = segment['text']
|
105 |
|
106 |
if translation_model:
|
107 |
text = translate_text(text, tokenizer, translation_model)
|
108 |
|
109 |
+
pdf.multi_cell(0, 10, f"{i + 1}. {text.strip()}") # No timestamps
|
110 |
|
111 |
pdf.output(output_file)
|
112 |
|
113 |
def write_ppt(transcription, output_file, tokenizer=None, translation_model=None):
|
114 |
+
"""Creates a PowerPoint presentation from the transcription without timestamps."""
|
115 |
ppt = Presentation()
|
116 |
|
117 |
for i, segment in enumerate(transcription['segments']):
|
|
|
|
|
118 |
text = segment['text']
|
119 |
|
120 |
if translation_model:
|
|
|
122 |
|
123 |
slide = ppt.slides.add_slide(ppt.slide_layouts[5]) # Blank slide
|
124 |
title = slide.shapes.title
|
125 |
+
title.text = f"{i + 1}. {text.strip()}" # No timestamps
|
126 |
|
127 |
ppt.save(output_file)
|
128 |
|