ttuleyb/tortoisetts-gui

GradioUI for TortoiseTTS voice generation

• 👋 Hi, I’m @ttuleyb, currently a student
• 👀 I’m interested in Data science and Software Engineering
• 💞️ I’m looking to collaborate on any projects using AI or software engineering in general

tortoisetts-gui's Issues

How I can use it

I ran the gradioui installed the tortoise TTS and have it working but if I run the gradio I get this error To create a public link, set share=True in launch().
Traceback (most recent call last):
File "C:\Users\UZR\anaconda3\envs\tortoise-tts\lib\site-packages\gradio\routes.py", line 321, in run_predict
output = await app.blocks.process_api(
File "C:\Users\UZR\anaconda3\envs\tortoise-tts\lib\site-packages\gradio\blocks.py", line 1015, in process_api
result = await self.call_function(fn_index, inputs, iterator, request)
File "C:\Users\UZR\anaconda3\envs\tortoise-tts\lib\site-packages\gradio\blocks.py", line 856, in call_function
prediction = await anyio.to_thread.run_sync(
File "C:\Users\UZR\anaconda3\envs\tortoise-tts\lib\site-packages\anyio\to_thread.py", line 31, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "C:\Users\UZR\anaconda3\envs\tortoise-tts\lib\site-packages\anyio_backends_asyncio.py", line 937, in run_sync_in_worker_thread
return await future
File "C:\Users\UZR\anaconda3\envs\tortoise-tts\lib\site-packages\anyio_backends_asyncio.py", line 867, in run
result = context.run(func, *args)
File "E:\DB\Tortoise\tortoise-tts\tortoise\gradioui.py", line 51, in text_to_speech
files = convert_text_to_speech(text, voiceSymbol, presetSymbol, numOfOutputs)
File "E:\DB\Tortoise\tortoise-tts\tortoise\tortoise_api.py", line 30, in convert_text_to_speech
gen = tts.tts_with_preset(text, voice_samples=reference_clips, preset=preset, k=numOfOutputs, verbose=False) #Generate speech
File "E:\DB\Tortoise\tortoise-tts\tortoise\api.py", line 328, in tts_with_preset
return self.tts(text, **settings)
File "E:\DB\Tortoise\tortoise-tts\tortoise\api.py", line 392, in tts
auto_conditioning, diffusion_conditioning, auto_conds, _ = self.get_conditioning_latents(voice_samples, return_mels=True)
File "E:\DB\Tortoise\tortoise-tts\tortoise\api.py", line 274, in get_conditioning_latents
auto_conds = torch.stack(auto_conds, dim=1)
RuntimeError: stack expects a non-empty TensorList

I modified tortoise-api.py and the gradio with the list of the voices I want to use
#Cache things for faster access
characterSymbols = {"Nev": "NLG"}
characters = dict.values(characterSymbols) and this in the gradio presetSymbols = {'ultra fast':'ultra_fast', 'fast':'fast', 'standard':'standard', 'high quality': 'high_quality'}
characterSymbols = {"Nev": "NLG"}

The idea of the gui is brilliant Idk how this is the only attempt to do a GUI for tortoise I could found I also don't understand how to use the readEntireBook.py I would appreciate it if you could explain also that prompt scraper you working on looks like another thing I want to use Thank you.