""" Resources lifted from across https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/86ed98aacaa8b2037aad795abd11cdca122cf39f - These could not be imported from their respective files because of missing args etc copyright: RVC-Project license: MIT """ from fairseq import checkpoint_utils import torch import ffmpeg import numpy as np import traceback import os import app.rvc.config from app.rvc.infer_pack.models import ( SynthesizerTrnMs256NSFsid, SynthesizerTrnMs256NSFsid_nono, SynthesizerTrnMs768NSFsid, SynthesizerTrnMs768NSFsid_nono, ) from app.rvc.vc_infer_pipeline import VC config = app.rvc.config.Config() # https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/86ed98aacaa8b2037aad795abd11cdca122cf39f/infer_batch_rvc.py#L126 def load_hubert(path): global hubert_model models, _, _ = checkpoint_utils.load_model_ensemble_and_task( [path], 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 # https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/86ed98aacaa8b2037aad795abd11cdca122cf39f/infer-web.py#L403 def get_vc(sid, weight_root, to_return_protect0, to_return_protect1): global n_spk, tgt_sr, net_g, vc, cpt, version if sid == "" or sid == []: global hubert_model if hubert_model is not 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) version = cpt.get("version", "v1") if version == "v1": if if_f0 == 1: net_g = SynthesizerTrnMs256NSFsid( *cpt["config"], is_half=config.is_half ) else: net_g = SynthesizerTrnMs256NSFsid_nono(*cpt["config"]) elif version == "v2": if if_f0 == 1: net_g = SynthesizerTrnMs768NSFsid( *cpt["config"], is_half=config.is_half ) else: net_g = SynthesizerTrnMs768NSFsid_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 == 0: to_return_protect0 = to_return_protect1 = { "visible": False, "value": 0.5, "__type__": "update", } else: to_return_protect0 = { "visible": True, "value": to_return_protect0, "__type__": "update", } to_return_protect1 = { "visible": True, "value": to_return_protect1, "__type__": "update", } version = cpt.get("version", "v1") if version == "v1": if if_f0 == 1: net_g = SynthesizerTrnMs256NSFsid(*cpt["config"], is_half=config.is_half) else: net_g = SynthesizerTrnMs256NSFsid_nono(*cpt["config"]) elif version == "v2": if if_f0 == 1: net_g = SynthesizerTrnMs768NSFsid(*cpt["config"], is_half=config.is_half) else: net_g = SynthesizerTrnMs768NSFsid_nono(*cpt["config"]) del net_g.enc_q print(net_g.load_state_dict(cpt["weight"], strict=False)) 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] return ( {"visible": True, "maximum": n_spk, "__type__": "update"}, to_return_protect0, to_return_protect1, ) # https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/86ed98aacaa8b2037aad795abd11cdca122cf39f/my_utils.py#L5 def load_audio(file, sr): try: # https://github.com/openai/whisper/blob/main/whisper/audio.py#L26 # This launches a subprocess to decode audio while down-mixing and resampling as necessary. # Requires the ffmpeg CLI and `ffmpeg-python` package to be installed. file = ( file.strip(" ").strip('"').strip("\n").strip('"').strip(" ") ) # 防止小白拷路径头尾带了空格和"和回车 out, _ = ( ffmpeg.input(file, threads=0) .output("-", format="f32le", acodec="pcm_f32le", ac=1, ar=sr) .run(cmd=["ffmpeg", "-nostdin"], capture_stdout=True, capture_stderr=True) ) except Exception as e: raise RuntimeError(f"Failed to load audio: {e}") return np.frombuffer(out, np.float32).flatten() # https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/86ed98aacaa8b2037aad795abd11cdca122cf39f/infer-web.py#L160 def vc_single( sid, input_audio_path, f0_up_key, f0_file, f0_method, file_index, file_index2, # file_big_npy, index_rate, filter_radius, resample_sr, rms_mix_rate, protect, ): # spk_item, input_audio0, vc_transform0,f0_file,f0method0 global tgt_sr, net_g, vc, hubert_model, version if input_audio_path is None: return "You need to upload an audio", None f0_up_key = int(f0_up_key) try: audio = load_audio(input_audio_path, 16000) audio_max = np.abs(audio).max() / 0.95 if audio_max > 1: audio /= audio_max times = [0, 0, 0] if not hubert_model: load_hubert() if_f0 = cpt.get("f0", 1) file_index = ( ( file_index.strip(" ") .strip('"') .strip("\n") .strip('"') .strip(" ") .replace("trained", "added") ) if file_index != "" else file_index2 ) # 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, input_audio_path, times, f0_up_key, f0_method, file_index, # file_big_npy, index_rate, if_f0, filter_radius, tgt_sr, resample_sr, rms_mix_rate, version, protect, f0_file=f0_file, ) if tgt_sr != resample_sr >= 16000: tgt_sr = resample_sr index_info = ( "Using index:%s." % file_index if os.path.exists(file_index) else "Index not used." ) return "Success.\n %s\nTime:\n npy:%ss, f0:%ss, infer:%ss" % ( index_info, times[0], times[1], times[2], ), (tgt_sr, audio_opt) except: info = traceback.format_exc() print(info) return info, (None, None)