I am trying to deploy the following trained (new voices cloned) multilingual YourTTS model:
YourTTS Model with 60+ Voices from Huggingface
The model is associated with the following YouTube video:
Now for Download: YourTTS (English, French, German, Spanish) Multilingual Model with 60+ Voices
I am trying to run the model locally on my WINDOWS laptop. I am using the following command line prompt to run the model:
python synthesize.py --text "This is a test sentence." --out_path "C:/Users/Home/OneDrive/Projects/Projects/QuranBeheld/scripts/coqui_TTS/nanonomad_models/output.wav" --model_path "c:/Users/Home/Environments/quranbeheld3.10.11/Lib/site-packages/TTS/nanonomad_models/checkpoint_1978000.pth" --config_path "c:/Users/Home/Environments/quranbeheld3.10.11/Lib/site-packages/TTS/nanonomad_models/config.json" --speakers_file_path "C:/Users/Home/OneDrive/Projects/Projects/QuranBeheld/scripts/coqui_TTS/nanonomad_models/speaker_ids.json" --speaker_idx "VCTK_johnw"
As I was getting 'File Not Found' errors, so I had to modify the config.json file to make references to the appropriate files on my local system (can be downloaded from here). As I was still getting error (different ones) I then manually created the speaker_ids.json file (can be downloaded from here).
I am currently getting the error:
File "C:\Users\Home\Environments\lib\site-packages\TTS\tts\utils\managers.py", line 194, in <setcomp>
speakers = sorted({x["name"] for x in embeddings.values()})
TypeError: 'int' object is not subscriptable
How may I to proceed to get this new model working?
Thanks.
