python – Error while installing Tortoise TTS using the Conda (CPU only PyTorch install)

I’ve been trying to install Tortoise TTS on my local computer with AMD Integrated Graphics so from the site as I don’t have NVIDIA GPU I can’t install the CUDA version, also can’t use the ROCm version as the site says its not supported on Windows for some reason. So I went with the CPU only install for PyTorch.

I have installed the required files from the github repo – github.com/neonbjb/tortoise-tts
and have followed the steps from the installation tutorial using Conda (miniconda) and have installed from the requirements.txt file and the setup.py file.

But on running the following command I get an error –

(tortoise) C:\Users\KIIT\tortoise-tts-main>python tortoise/do_tts.py --text "I'm going to speak this" --voice random --preset fast
Traceback (most recent call last):
  File "tortoise/do_tts.py", line 7, in <module>
    from api import TextToSpeech, MODELS_DIR
  File "C:\Users\KIIT\tortoise-tts-main\tortoise\api.py", line 9, in <module>
    import progressbar
ModuleNotFoundError: No module named 'progressbar'

I can’t seem to figure out which part of the installation went wrong. If anyone knows how to solve this and install Tortoise, please do help me out.

I’ve tried to quite a few tutorials I could find to install Tortoise but I keep running into errors and dependency issues so I took the conda way. I expected for the above command to generate the output WAV file as the demo says but there seems to be some modules missing which I can’t figure out why as I followed all the instructions as they were.