Amphion icon indicating copy to clipboard operation
Amphion copied to clipboard

[Docs]: Potential mistake about valle inference page

Open mangoszteen opened this issue 4 months ago • 0 comments

Documentation Reference

https://github.com/open-mmlab/Amphion/tree/main/egs/tts/VALLE

Feedback on documentation

The inference part suggests that: The format of test list file is text|text_prompt|audio_prompt

However, according to the inference_for_batches() function in valle_inference.py:

def inference_for_batches(self):
    test_list_file = self.args.test_list_file
    assert test_list_file is not None

    pred_res = []
    with open(test_list_file, "r") as fin:
        for idx, line in enumerate(fin.readlines()):
            fields = line.strip().split("|")
            if self.args.continual:
                assert len(fields) == 2
                text_prompt, audio_prompt_path = fields
                text = ""
            else:
                assert len(fields) == 3
                text_prompt, audio_prompt_path, text = fields

The order of test list file seems to be text_prompt|audio_prompt|text.

Additional context

(Add any other context or screenshots about the documentation here.)

mangoszteen avatar Sep 11 '25 12:09 mangoszteen