github/ebook2audiobook
1
1
Fork 0
mirror of https://github.com/DrewThomasson/ebook2audiobook.git synced 2026-01-10 14:28:15 -05:00
Code Issues Packages Projects Releases Wiki Activity

...

Browse Source
This commit is contained in:
unknown
2025-12-22 04:41:55 -08:00
parent 382600d3ec
commit 4f8fe033ff
6 changed files with 17 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
lib/classes/tts_engines/bark.py
View File

@@ -13,11 +13,12 @@ class Bark(TTSUtils, TTSRegistry, name='bark'):
self.pth_voice_file = None
self.sentences_total_time = 0.0
self.sentence_idx = 1
self.resampler_cache = {}
self.audio_segments = []
self.models = load_engine_presets(self.session['tts_engine'])
self.params = {}
self.params['samplerate'] = self.models[self.session['fine_tuned']]['samplerate']
self.vtt_path = os.path.join(self.session['process_dir'],Path(self.session['final_name']).stem+'.vtt')
self.resampler_cache = {}
self.audio_segments = []
using_gpu = self.session['device'] != devices['CPU']['proc']
enough_vram = self.session['free_vram_gb'] > 4.0
seed = 123456

5
lib/classes/tts_engines/fairseq.py
View File

@@ -13,11 +13,12 @@ class Fairseq(TTSUtils, TTSRegistry, name='fairseq'):
self.pth_voice_file = None
self.sentences_total_time = 0.0
self.sentence_idx = 1
self.resampler_cache = {}
self.audio_segments = []
self.models = load_engine_presets(self.session['tts_engine'])
self.params = {"semitones":{}}
self.params['samplerate'] = self.models[self.session['fine_tuned']]['samplerate']
self.vtt_path = os.path.join(self.session['process_dir'],Path(self.session['final_name']).stem+'.vtt')
self.resampler_cache = {}
self.audio_segments = []
using_gpu = self.session['device'] != devices['CPU']['proc']
enough_vram = self.session['free_vram_gb'] > 4.0
seed = 123456

5
lib/classes/tts_engines/tacotron.py
View File

@@ -13,11 +13,12 @@ class Tacotron2(TTSUtils, TTSRegistry, name='tacotron'):
self.pth_voice_file = None
self.sentences_total_time = 0.0
self.sentence_idx = 1
self.resampler_cache = {}
self.audio_segments = []
self.models = load_engine_presets(self.session['tts_engine'])
self.params = {"semitones":{}}
self.params['samplerate'] = self.models[self.session['fine_tuned']]['samplerate']
self.vtt_path = os.path.join(self.session['process_dir'],Path(self.session['final_name']).stem+'.vtt')
self.resampler_cache = {}
self.audio_segments = []
using_gpu = self.session['device'] != devices['CPU']['proc']
enough_vram = self.session['free_vram_gb'] > 4.0
seed = 123456

5
lib/classes/tts_engines/vits.py
View File

@@ -13,11 +13,12 @@ class Vits(TTSUtils, TTSRegistry, name='vits'):
self.pth_voice_file = None
self.sentences_total_time = 0.0
self.sentence_idx = 1
self.resampler_cache = {}
self.audio_segments = []
self.models = load_engine_presets(self.session['tts_engine'])
self.params = {"semitones":{}}
self.params['samplerate'] = self.models[self.session['fine_tuned']]['samplerate']
self.vtt_path = os.path.join(self.session['process_dir'],Path(self.session['final_name']).stem+'.vtt')
self.resampler_cache = {}
self.audio_segments = []
using_gpu = self.session['device'] != devices['CPU']['proc']
enough_vram = self.session['free_vram_gb'] > 4.0
seed = 123456

5
lib/classes/tts_engines/xtts.py
View File

@@ -13,11 +13,12 @@ class XTTSv2(TTSUtils, TTSRegistry, name='xtts'):
self.pth_voice_file = None
self.sentences_total_time = 0.0
self.sentence_idx = 1
self.resampler_cache = {}
self.audio_segments = []
self.models = load_engine_presets(self.session['tts_engine'])
self.params = {"latent_embedding":{}}
self.params['samplerate'] = self.models[self.session['fine_tuned']]['samplerate']
self.vtt_path = os.path.join(self.session['process_dir'],Path(self.session['final_name']).stem+'.vtt')
self.resampler_cache = {}
self.audio_segments = []
using_gpu = self.session['device'] != devices['CPU']['proc']
enough_vram = self.session['free_vram_gb'] > 4.0
seed = 123456

4
lib/classes/tts_engines/yourtts.py
View File

@@ -13,12 +13,12 @@ class YourTTS(TTSUtils, TTSRegistry, name='yourtts'):
self.pth_voice_file = None
self.sentences_total_time = 0.0
self.sentence_idx = 1
self.resampler_cache = {}
self.audio_segments = []
self.models = load_engine_presets(self.session['tts_engine'])
self.params = {}
self.params['samplerate'] = self.models[self.session['fine_tuned']]['samplerate']
self.vtt_path = os.path.join(self.session['process_dir'],Path(self.session['final_name']).stem+'.vtt')
self.resampler_cache = {}
self.audio_segments = []
using_gpu = self.session['device'] != devices['CPU']['proc']
enough_vram = self.session['free_vram_gb'] > 4.0
seed = 123456