Added CLI functionality for inference! No need to use the GUI for inference. Added an audio-outputs directory

README.md

@@ -52,6 +52,7 @@ Special thanks to discord user @kalomaze#2983 for creating a temporary colab not
 + Added CLI functionality
   + added train-index-cli.py to train the feature index without the GUI
   + added extract-small-model.py to extract the small model without the GUI
+  + added infer-cli.py to do inference without the GUI.
 
 ## This repository has the following features too:
 + Reduce tone leakage by replacing source feature to training-set feature using top1 retrieval;
@@ -193,6 +194,22 @@ python train-index-cli.py mi-test
 python extract-small-model-cli.py logs/G_99750.pth MyModel 40k 1 "This is a cool model."
 ```
 
+## Inference without the GUI (Voice Conversion)
+```bash
+# + Mangio-RVC-Fork Feature. Infer audio with just the CLI
+# Arguments
+# arg1 = model name in weights folder. (mi-test.pth)
+# arg2 = source file path (.wav)
+# arg3 = output file name to be placed in ./audio-outputs (myoutput.wav).
+# arg4 = feature index file path. (E:\added_IVF3042_Flat_nprobe_1.index)
+# arg5 = speaker ID (0)
+# arg6 = transposition. (12 = 12 semitones up)
+# arg7 = f0 method. (harvest, pm, crepe, dio, crepe-tiny)
+# arg8 = crepe hop length. Use 128. (applies to crepe f0 method only)
+# arg9 = feature index ratio (0.78)
+python infer-cli.py mi-test.pth E:\my-source-file.wav conversion_output.wav E:\added_IVF3042_Flat_nprobe_1.index 0 -2 pm 128 0.78
+```
+
 # Running the Tensorboard 📉
 ```bash
 cd Mangio-RVC-Fork

config.py

@@ -4,20 +4,21 @@ from multiprocessing import cpu_count
 
 
 class Config:
-    def __init__(self):
+    def __init__(self, is_gui=True):
         self.device = "cuda:0"
         self.is_half = True
         self.n_cpu = 0
         self.gpu_name = None
         self.gpu_mem = None
-        (
+        if(is_gui):
-            self.python_cmd,
+            (
-            self.listen_port,
+                self.python_cmd,
-            self.iscolab,
+                self.listen_port,
-            self.noparallel,
+                self.iscolab,
-            self.noautoopen,
+                self.noparallel,
-            self.paperspace,
+                self.noautoopen,
-        ) = self.arg_parse()
+                self.paperspace,
+            ) = self.arg_parse()
         
         self.x_pad, self.x_query, self.x_center, self.x_max = self.device_config()
 

extract-small-model-cli.py

@@ -1,3 +1,5 @@
+# Fork Feature Mangio RVC Fork. Extract the small model from a checkpoint with CLI.
+
 import sys
 from train.process_ckpt import extract_small_model
 

infer-cli.py

@@ -0,0 +1,181 @@
+# Fork Feature Mangio RVC Fork. Infer Audio with just the CLI
+
+import torch, os, traceback, sys, warnings, shutil, numpy as np
+
+from infer_pack.models import SynthesizerTrnMs256NSFsid, SynthesizerTrnMs256NSFsid_nono
+from fairseq import checkpoint_utils
+from vc_infer_pipeline import VC
+from config import Config
+from my_utils import load_audio
+
+# Fork Feature. Write an audio file
+from scipy.io.wavfile import write
+
+config = Config(is_gui=False)
+
+
+weight_root = 'weights'
+
+n_spk = None # Set from get_vc
+tgt_sr = 0 # Set from get_vc
+net_g = None # Set from get_vc
+vc = None # Set from get_vc
+cpt = None # Set from get_vc
+
+hubert_model = None # Set from vc_single
+
+def get_hubert():
+    models, _, _ = checkpoint_utils.load_model_ensemble_and_task(
+        ["hubert_base.pt"],
+        suffix="",
+    )
+    hubert_model = models[0]
+    hubert_model = hubert_model.to(config.device)
+    if config.is_half:
+        hubert_model = hubert_model.half()
+    else:
+        hubert_model = hubert_model.float()
+    hubert_model.eval()
+    return hubert_model
+
+def get_vc(sid):
+    global n_spk, tgt_sr, net_g, vc, cpt
+    if sid == []:
+        global hubert_model
+        if hubert_model != None:  # 考虑到轮询, 需要加个判断看是否 sid 是由有模型切换到无模型的
+            print("clean_empty_cache")
+            del net_g, n_spk, vc, hubert_model, tgt_sr  # ,cpt
+            hubert_model = net_g = n_spk = vc = hubert_model = tgt_sr = None
+            if torch.cuda.is_available():
+                torch.cuda.empty_cache()
+            ###楼下不这么折腾清理不干净
+            if_f0 = cpt.get("f0", 1)
+            if if_f0 == 1:
+                net_g = SynthesizerTrnMs256NSFsid(
+                    *cpt["config"], is_half=config.is_half
+                )
+            else:
+                net_g = SynthesizerTrnMs256NSFsid_nono(*cpt["config"])
+            del net_g, cpt
+            if torch.cuda.is_available():
+                torch.cuda.empty_cache()
+            cpt = None
+        return {"visible": False, "__type__": "update"}
+    person = "%s/%s" % (weight_root, sid)
+    print("loading %s" % person)
+    cpt = torch.load(person, map_location="cpu")
+    tgt_sr = cpt["config"][-1]
+    cpt["config"][-3] = cpt["weight"]["emb_g.weight"].shape[0]  # n_spk
+    if_f0 = cpt.get("f0", 1)
+    if if_f0 == 1:
+        net_g = SynthesizerTrnMs256NSFsid(*cpt["config"], is_half=config.is_half)
+    else:
+        net_g = SynthesizerTrnMs256NSFsid_nono(*cpt["config"])
+    del net_g.enc_q
+    print(net_g.load_state_dict(cpt["weight"], strict=False))  # 不加这一行清不干净, 真奇葩
+    net_g.eval().to(config.device)
+    if config.is_half:
+        net_g = net_g.half()
+    else:
+        net_g = net_g.float()
+    vc = VC(tgt_sr, config)
+    n_spk = cpt["config"][-3]
+    print("Mangio-RVC-Fork Infer-CLI: Model has been loaded...")
+    return {"visible": True, "maximum": n_spk, "__type__": "update"}
+
+def vc_single(
+    sid,
+    input_audio,
+    f0_up_key,
+    f0_file,
+    f0_method,
+    file_index,
+    # file_big_npy,
+    index_rate,
+    crepe_hop_length,
+):  # spk_item, input_audio0, vc_transform0,f0_file,f0method0
+    global tgt_sr, net_g, vc, hubert_model, cpt
+    if input_audio is None:
+        return "You need to upload an audio", None
+    f0_up_key = int(f0_up_key)
+    try:
+        audio = load_audio(input_audio, 16000)
+        times = [0, 0, 0]
+        if hubert_model == None:
+            hubert_model = get_hubert()
+        if_f0 = cpt.get("f0", 1)
+        file_index = (
+            file_index.strip(" ")
+            .strip('"')
+            .strip("\n")
+            .strip('"')
+            .strip(" ")
+            .replace("trained", "added")
+        )  # 防止小白写错，自动帮他替换掉
+        # file_big_npy = (
+        #     file_big_npy.strip(" ").strip('"').strip("\n").strip('"').strip(" ")
+        # )
+        audio_opt = vc.pipeline(
+            hubert_model,
+            net_g,
+            sid,
+            audio,
+            times,
+            f0_up_key,
+            f0_method,
+            file_index,
+            # file_big_npy,
+            index_rate,
+            if_f0,
+            crepe_hop_length,
+            f0_file=f0_file,
+        )
+        print(
+            "npy: ", times[0], "s, f0: ", times[1], "s, infer: ", times[2], "s", sep=""
+        )
+        return "Success", (tgt_sr, audio_opt)
+    except:
+        info = traceback.format_exc()
+        print(info)
+        return info, (None, None)
+
+def start_inference():
+    # Get Essential Paths first
+    model_name = str(sys.argv[1]) # MyModel.pth
+    source_audio_path = str(sys.argv[2]) # Source Audio Path
+    output_file_name = str(sys.argv[3]) # Output audio path e.g outputs/conversion_out.wav
+    feature_index_path = str(sys.argv[4]) # Feature Index file path
+    f0_file = None # Not implemented yet. To be implemented later on
+
+    # Get parameters for inference
+    speaker_id = int(sys.argv[5]) # 0
+    transposition = float(sys.argv[6]) # 0.0 float
+    f0_method = str(sys.argv[7]) # harvest
+    crepe_hop_length = int(sys.argv[8]) # 128
+    feature_ratio = float(sys.argv[9]) # 0.78
+
+    # Get VC first. set global vc to VC from pipeline script
+    print("Mangio-RVC-Fork Infer-CLI: Starting the inference...")
+    vc_data = get_vc(model_name)
+    print(vc_data)
+    print("Mangio-RVC-Fork Infer-CLI: Performing inference...")
+    conversion_data = vc_single(
+        speaker_id,
+        source_audio_path,
+        transposition,
+        f0_file,
+        f0_method,
+        feature_index_path,
+        feature_ratio,
+        crepe_hop_length
+    )
+    if(conversion_data[0] == "Success"):
+        print("Mangio-RVC-Fork Infer-CLI: Inference succeeded. Writing to %s/%s..." % ('audio-outputs', output_file_name))
+        # Go ahead with output
+        write('%s/%s' % ('audio-outputs', output_file_name), conversion_data[1][0], conversion_data[1][1])
+        print("Mangio-RVC-Fork Infer-CLI: Finished! Saved output to %s/%s" % ('audio-outputs', output_file_name))
+    else:
+        print("Mangio-RVC-Fork Infer-CLI: Inference failed. Here's the traceback: ")
+        print(conversion_data[0])
+
+start_inference()