Add FF and refactor a little

app.py

@@ -31,18 +31,15 @@ limitation = os.getenv("SYSTEM") == "spaces"
 
 config = Config()
 
+# Edge TTS
 edge_output_filename = "edge_output.mp3"
 tts_voice_list = asyncio.get_event_loop().run_until_complete(edge_tts.list_voices())
 tts_voices = [f"{v['ShortName']}-{v['Gender']}" for v in tts_voice_list]
 
+# RVC models
 model_root = "weights"
 models = [d for d in os.listdir(model_root) if os.path.isdir(f"{model_root}/{d}")]
 models.sort()
-hubert_model = None
-
-print("Loading rmvpe model...")
-rmvpe_model = RMVPE("rmvpe.pt", config.is_half, config.device)
-print("rmvpe model loaded.")
 
 
 def model_data(model_name):
@@ -97,7 +94,7 @@ def model_data(model_name):
 
 
 def load_hubert():
-    global hubert_model
+    # global hubert_model
     models, _, _ = checkpoint_utils.load_model_ensemble_and_task(
         ["hubert_base.pt"],
         suffix="",
@@ -108,7 +105,7 @@ def load_hubert():
         hubert_model = hubert_model.half()
     else:
         hubert_model = hubert_model.float()
-    hubert_model.eval()
+    return hubert_model.eval()
 
 
 def tts(
@@ -128,7 +125,7 @@ def tts(
     print(datetime.datetime.now())
     print("tts_text:")
     print(tts_text)
-    print(f"tts_voice: {tts_voice}")
+    print(f"tts_voice: {tts_voice}, speed: {speed}")
     print(f"Model name: {model_name}")
     print(f"F0: {f0_method}, Key: {f0_up_key}, Index: {index_rate}, Protect: {protect}")
     try:
@@ -139,7 +136,6 @@ def tts(
                 None,
                 None,
             )
-        tgt_sr, net_g, vc, version, index_file, if_f0 = model_data(model_name)
         t0 = time.time()
         if speed >= 0:
             speed_str = f"+{speed}%"
@@ -162,11 +158,9 @@ def tts(
                 edge_output_filename,
                 None,
             )
-
         f0_up_key = int(f0_up_key)
 
-        if not hubert_model:
-            load_hubert()
+        tgt_sr, net_g, vc, version, index_file, if_f0 = model_data(model_name)
         if f0_method == "rmvpe":
             vc.model_rmvpe = rmvpe_model
         times = [0, 0, 0]
@@ -201,9 +195,11 @@ def tts(
             (tgt_sr, audio_opt),
         )
     except EOFError:
-        info = """
-It seems that edge-tts output is empty. This may occur when the input text and the speaker do not match.
-For example, maybe you entered Japanese (without alphabets) text but chose non-Japanese speaker?"""
+        info = (
+            "It seems that the edge-tts output is not valid. "
+            "This may occur when the input text and the speaker do not match. "
+            "For example, maybe you entered Japanese (without alphabets) text but chose non-Japanese speaker?"
+        )
         print(info)
         return info, None, None
     except:
@@ -212,6 +208,14 @@ For example, maybe you entered Japanese (without alphabets) text but chose non-J
         return info, None, None
 
 
+print("Loading hubert model...")
+hubert_model = load_hubert()
+print("Hubert model loaded.")
+
+print("Loading rmvpe model...")
+rmvpe_model = RMVPE("rmvpe.pt", config.is_half, config.device)
+print("rmvpe model loaded.")
+
 initial_md = """
 # RVC text-to-speech demo
 

requirements.txt

@@ -1,4 +1,3 @@
-# Cython==0.29.34
 edge_tts==6.1.7
 fairseq==0.12.2
 faiss_cpu==1.7.4

weights/FF/FF.index

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:586dd540bc384163e2107df8b48c2a1d21cc1e89b5eef1c050d0dc12544ebd24
+size 508489659

weights/FF/FF_e300.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f1f037b3c249418806317a14dd12d5fcabef908a52bc2f1ba2c83ca34569d49
+size 55232064