seamless_communication
seamless_communication copied to clipboard
typo & error in expressivity_predict example
from the readme:
expressivity_predict <path_to_input_audio> --tgt_lang <tgt_lang> --model_name seamless_expressivity --vocoder_name vocoder_pretssel --output--path <path_to_save_audio>
the correct flag is --output_path, not --output--path
running this also results in:
(wslenv) martin@Desktop:/mnt/c/users/shkre/code/seamless/seamless_communication$ expressivity_predict 7.wav --tgt_lang spa --model_name seamless_expressivity --vocoder_name vocoder_pretssel --output_path .
2023-12-10 16:12:24,290 INFO -- seamless_communication.cli.expressivity.predict.predict: Running inference on device=device(type='cuda', index=0) with dtype=torch.float16.
Traceback (most recent call last):
File "/mnt/c/users/shkre/code/seamless/wslenv/bin/expressivity_predict", line 8, in
despite being logged in and having access to the gated model.