Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-11-22 08:07:56 +01:00
Code Issues Packages Projects Releases Wiki Activity

Unescape model output for silero/elevenlabs

Browse Source
This commit is contained in:
oobabooga 2023-08-24 17:27:12 -07:00
parent 3320accfdc
commit a2c67262c7
2 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
extensions/elevenlabs_tts/script.py
View File

@ -1,3 +1,4 @@
import html
import re import re
from pathlib import Path from pathlib import Path
@ -111,7 +112,7 @@ def output_modifier(string):
output_file = Path(f'extensions/elevenlabs_tts/outputs/{wav_idx:06d}.mp3'.format(wav_idx)) output_file = Path(f'extensions/elevenlabs_tts/outputs/{wav_idx:06d}.mp3'.format(wav_idx))
print(f'Outputting audio to {str(output_file)}') print(f'Outputting audio to {str(output_file)}')
try: try:
audio = elevenlabs.generate(text=string, voice=params['selected_voice'], model=params['model']) audio = elevenlabs.generate(text=html.unescape(string), voice=params['selected_voice'], model=params['model'])
elevenlabs.save(audio, str(output_file)) elevenlabs.save(audio, str(output_file))
autoplay = 'autoplay' if params['autoplay'] else '' autoplay = 'autoplay' if params['autoplay'] else ''

3
extensions/silero_tts/script.py
View File

@ -1,3 +1,4 @@
import html
import random import random
import time import time
from pathlib import Path from pathlib import Path
@ -125,7 +126,7 @@ def output_modifier(string, state):
else: else:
output_file = Path(f'extensions/silero_tts/outputs/{state["character_menu"]}_{int(time.time())}.wav') output_file = Path(f'extensions/silero_tts/outputs/{state["character_menu"]}_{int(time.time())}.wav')
prosody = '<prosody rate="{}" pitch="{}">'.format(params['voice_speed'], params['voice_pitch']) prosody = '<prosody rate="{}" pitch="{}">'.format(params['voice_speed'], params['voice_pitch'])
silero_input = f'<speak>{prosody}{xmlesc(string)}</prosody></speak>' silero_input = f'<speak>{prosody}{xmlesc(html.unescape(string))}</prosody></speak>'
model.save_wav(ssml_text=silero_input, speaker=params['speaker'], sample_rate=int(params['sample_rate']), audio_path=str(output_file)) model.save_wav(ssml_text=silero_input, speaker=params['speaker'], sample_rate=int(params['sample_rate']), audio_path=str(output_file))
autoplay = 'autoplay' if params['autoplay'] else '' autoplay = 'autoplay' if params['autoplay'] else ''