do_tty.py gives CUFF error

[iplayfast]

python tortoise/do_tts.py --text "I'm going to speak this" --voice random --preset fast

seems to work, but specifying the voice doesn't.

python tortoise/do_tts.py --text "I'm going to speak this" --voice train_atkins --preset fast Traceback (most recent call last): File "/home/chris/ai/voice/tortoise-tts/tortoise/do_tts.py", line 41, in gen, dbg_state = tts.tts_with_preset(args.text, k=args.candidates, voice_samples=voice_samples, conditioning_latents=conditioning_latents, File "/home/chris/ai/voice/tortoise-tts/tortoise/api.py", line 346, in tts_with_preset return self.tts(text, **settings) File "/home/chris/ai/voice/tortoise-tts/tortoise/api.py", line 409, in tts auto_conditioning, diffusion_conditioning, auto_conds, _ = self.get_conditioning_latents(voice_samples, return_mels=True) File "/home/chris/ai/voice/tortoise-tts/tortoise/api.py", line 291, in get_conditioning_latents auto_conds.append(format_conditioning(vs, device=self.device)) File "/home/chris/ai/voice/tortoise-tts/tortoise/api.py", line 113, in format_conditioning mel_clip = TorchMelSpectrogram()(clip.unsqueeze(0)).squeeze(0) File "/home/chris/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl return forward_call(*input, **kwargs) File "/home/chris/.local/lib/python3.10/site-packages/tortoise/models/arch_util.py", line 325, in forward mel = self.mel_stft(inp) File "/home/chris/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl return forward_call(*input, **kwargs) File "/home/chris/.local/lib/python3.10/site-packages/torchaudio/transforms/_transforms.py", line 642, in forward specgram = self.spectrogram(waveform) File "/home/chris/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl return forward_call(*input, **kwargs) File "/home/chris/.local/lib/python3.10/site-packages/torchaudio/transforms/_transforms.py", line 108, in forward return F.spectrogram( File "/home/chris/.local/lib/python3.10/site-packages/torchaudio/functional/functional.py", line 121, in spectrogram spec_f = torch.stft( File "/home/chris/.local/lib/python3.10/site-packages/torch/functional.py", line 632, in stft return _VF.stft(input, n_fft, hop_length, win_length, window, # type: ignore[attr-defined] RuntimeError: cuFFT error: CUFFT_INTERNAL_ERROR

[Qifeng-Wu99]

It seems that this issus is related to cuda-11.7, I am good with 11.8 and corresponding pytorch

[yoyo115956]

It seems that this issus is related to cuda-11.7, I am good with 11.8 and corresponding pytorch

Definitely addressed my problem, thank u!!!