mrleo1nid/ACE-Step
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix bugs and ad more info for install

Browse Source
This commit is contained in:
chuxij
2025-05-05 04:44:31 +00:00
parent f60abc289d
commit 11453db510
7 changed files with 77 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files
pipeline_ace_step.py
+2 -2
View File
@@ -158,7 +158,7 @@ class ACEStepPipeline:
])
self.lang_segment = lang_segment
self.lyric_tokenizer = VoiceBpeTokenizer()
text_encoder_model = UMT5EncoderModel.from_pretrained(text_encoder_checkpoint_path).eval()
text_encoder_model = UMT5EncoderModel.from_pretrained(text_encoder_checkpoint_path, torch_dtype=self.dtype).eval()
text_encoder_model = text_encoder_model.to(device).to(self.dtype)
text_encoder_model.requires_grad_(False)
self.text_encoder_model = text_encoder_model
@@ -941,7 +941,7 @@ class ACEStepPipeline:
output_path_flac = f"{base_path}/output_{time.strftime('%Y%m%d%H%M%S')}_{idx}.{format}"
target_wav = target_wav.float()
torchaudio.save(output_path_flac, target_wav, sample_rate=sample_rate, format=format, backend="ffmpeg", compression=torchaudio.io.CodecConfig(bit_rate=320000))
torchaudio.save(output_path_flac, target_wav, sample_rate=sample_rate, format=format)
return output_path_flac
def infer_latents(self, input_audio_path):