Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-31 14:33:54 -04:00
Code Issues Packages Projects Releases Wiki Activity

Make skipping overlay for files that generate no audio data more robust

Browse Source
This commit is contained in:
Kovid Goyal 2024-10-25 15:59:04 +05:30
parent 41e03e0433
commit b6af6218bb
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 13 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
src/calibre/ebooks/oeb/polish/tts.py
View File

@ -515,6 +515,17 @@ def embed_tts(container, report_progress=None, callback_to_download_voices=None)
return False return False
wav = io.BytesIO() wav = io.BytesIO()
wav.write(wav_header_for_pcm_data(size_of_audio_data, HIGH_QUALITY_SAMPLE_RATE)) wav.write(wav_header_for_pcm_data(size_of_audio_data, HIGH_QUALITY_SAMPLE_RATE))
durations = []
file_duration = 0
for i, s in enumerate(pfd.sentences):
audio_data, duration = audio_map[s]
if duration > 0:
wav.write(audio_data)
durations.append((s.elem_id, file_duration, duration))
file_duration += duration
if not file_duration:
continue
afitem = container.generate_item(name + '.m4a', id_prefix='tts-') afitem = container.generate_item(name + '.m4a', id_prefix='tts-')
pfd.audio_file_name = container.href_to_name(afitem.get('href'), container.opf_name) pfd.audio_file_name = container.href_to_name(afitem.get('href'), container.opf_name)
smilitem = container.generate_item(name + '.smil', id_prefix='smil-') smilitem = container.generate_item(name + '.smil', id_prefix='smil-')
@ -533,12 +544,8 @@ def embed_tts(container, report_progress=None, callback_to_download_voices=None)
seq.text = seq.text[:seq.text.find('X')] seq.text = seq.text[:seq.text.find('X')]
audio_href = container.name_to_href(pfd.audio_file_name, pfd.smil_file_name) audio_href = container.name_to_href(pfd.audio_file_name, pfd.smil_file_name)
html_href = container.name_to_href(pfd.name, pfd.smil_file_name) html_href = container.name_to_href(pfd.name, pfd.smil_file_name)
file_duration = 0 for elem_id, clip_start, duration in durations:
for i, s in enumerate(pfd.sentences): make_par(container, seq, html_href, audio_href, elem_id, clip_start, duration)
audio_data, duration = audio_map[s]
wav.write(audio_data)
make_par(container, seq, html_href, audio_href, s.elem_id, file_duration, duration)
file_duration += duration
if len(seq): if len(seq):
seq[-1].tail = seq.text[:-2] seq[-1].tail = seq.text[:-2]
wav.seek(0) wav.seek(0)