vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-10 09:04:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

tts.cpp merged and working in kcpp!

Browse source
This commit is contained in:
Concedo 2025-08-17 18:09:28 +08:00
parent 52606e9b1d
commit bcaf379509
5 changed files with 90 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

10
koboldcpp.py
View file

@ -5333,13 +5333,13 @@ def show_gui():
audio_tab = tabcontent["Audio"]
makefileentry(audio_tab, "Whisper Model (Speech-To-Text):", "Select Whisper .bin Model File", whisper_model_var, 1, width=280, filetypes=[("*.bin","*.bin")], tooltiptxt="Select a Whisper .bin model file on disk to be loaded for Voice Recognition.")
whisper_model_var.trace_add("write", gui_changed_modelfile)
makefileentry(audio_tab, "OuteTTS Model (Text-To-Speech Required):", "Select OuteTTS GGUF Model File", tts_model_var, 3, width=280, filetypes=[("*.gguf","*.gguf")], tooltiptxt="Select a OuteTTS GGUF model file on disk to be loaded for Narration.")
makefileentry(audio_tab, "TTS Model (Text-To-Speech):", "Select TTS GGUF Model File", tts_model_var, 3, width=280, filetypes=[("*.gguf","*.gguf")], tooltiptxt="Select a TTS GGUF model file on disk to be loaded for Narration.")
tts_model_var.trace_add("write", gui_changed_modelfile)
makelabelentry(audio_tab, "OuteTTS Threads:" , tts_threads_var, 5, 50,padx=290,singleline=True,tooltip="How many threads to use during TTS generation.\nIf left blank, uses same value as threads.")
makelabelentry(audio_tab, "OuteTTS Max Tokens:" , ttsmaxlen_var, 7, 50,padx=290,singleline=True,tooltip="Max allowed audiotokens to generate per TTS request.")
makelabelentry(audio_tab, "TTS Threads:" , tts_threads_var, 5, 50,padx=290,singleline=True,tooltip="How many threads to use during TTS generation.\nIf left blank, uses same value as threads.")
makelabelentry(audio_tab, "TTS Max Tokens:" , ttsmaxlen_var, 7, 50,padx=290,singleline=True,tooltip="Max allowed audiotokens to generate per TTS request.")
makecheckbox(audio_tab, "TTS Use GPU", ttsgpu_var, 9, 0,tooltiptxt="Uses the GPU for TTS.")
ttsgpu_var.trace_add("write", gui_changed_modelfile)
makefileentry(audio_tab, "WavTokenizer Model (Text-To-Speech Required):", "Select WavTokenizer GGUF Model File", wavtokenizer_var, 11, width=280, filetypes=[("*.gguf","*.gguf")], tooltiptxt="Select a WavTokenizer GGUF model file on disk to be loaded for Narration.")
makefileentry(audio_tab, "WavTokenizer Model (Required for OuteTTS):", "Select WavTokenizer GGUF Model File", wavtokenizer_var, 11, width=280, filetypes=[("*.gguf","*.gguf")], tooltiptxt="Select a WavTokenizer GGUF model file on disk to be loaded for Narration.")
wavtokenizer_var.trace_add("write", gui_changed_modelfile)
admin_tab = tabcontent["Admin"]
@ -7610,7 +7610,7 @@ if __name__ == '__main__':
whisperparsergroup.add_argument("--whispermodel", metavar=('[filename]'), help="Specify a Whisper .bin model to enable Speech-To-Text transcription.", default="")
ttsparsergroup = parser.add_argument_group('TTS Narration Commands')
ttsparsergroup.add_argument("--ttsmodel", metavar=('[filename]'), help="Specify the OuteTTS Text-To-Speech GGUF model.", default="")
ttsparsergroup.add_argument("--ttsmodel", metavar=('[filename]'), help="Specify the TTS Text-To-Speech GGUF model.", default="")
ttsparsergroup.add_argument("--ttswavtokenizer", metavar=('[filename]'), help="Specify the WavTokenizer GGUF model.", default="")
ttsparsergroup.add_argument("--ttsgpu", help="Use the GPU for TTS.", action='store_true')
ttsparsergroup.add_argument("--ttsmaxlen", help="Limit number of audio tokens generated with TTS.", type=int, default=default_ttsmaxlen)