update

app2.py

@@ -47,7 +47,9 @@ speed = 1.0
 # fix_duration = 27  # None or float (duration in seconds)
 fix_duration = None
 
-def load_model(exp_name, model_cls, model_cfg, ckpt_step):
+def load_model(repo_name, exp_name, model_cls, model_cfg, ckpt_step):
+    checkpoint = torch.load(str(cached_path(f"hf://SWivid/{repo_name}/{exp_name}/model_{ckpt_step}.pt")), map_location=device)
+
     checkpoint = torch.load(str(cached_path(f"hf://SWivid/F5-TTS/{exp_name}/model_{ckpt_step}.pt")), map_location=device)
     vocab_char_map, vocab_size = get_tokenizer("Emilia_ZH_EN", "pinyin")
     model = CFM(
@@ -77,8 +79,9 @@ def load_model(exp_name, model_cls, model_cfg, ckpt_step):
 F5TTS_model_cfg = dict(dim=1024, depth=22, heads=16, ff_mult=2, text_dim=512, conv_layers=4)
 E2TTS_model_cfg = dict(dim=1024, depth=24, heads=16, ff_mult=4)
 
-F5TTS_ema_model, F5TTS_base_model = load_model("F5TTS_Base", DiT, F5TTS_model_cfg, 1200000)
-E2TTS_ema_model, E2TTS_base_model = load_model("E2TTS_Base", UNetT, E2TTS_model_cfg, 1200000)
+F5TTS_ema_model = load_model("F5-TTS", "F5TTS_Base", DiT, F5TTS_model_cfg, 1200000)
+E2TTS_ema_model = load_model("E2-TTS", "E2TTS_Base", UNetT, E2TTS_model_cfg, 1200000)
+
 
 def chunk_text(text, max_chars=200):
     chunks = []