From 36456e3908b63de57fa7670dd6db7f731dc13970 Mon Sep 17 00:00:00 2001 From: Ftps <63702646+Tps-F@users.noreply.github.com> Date: Tue, 19 Sep 2023 21:15:30 +0900 Subject: [PATCH] replace warn (#1255) --- infer-web.py | 4 +- infer/lib/train/data_utils.py | 4 +- infer/lib/train/utils.py | 8 +- infer/modules/train/train.py | 2 +- infer/modules/vc/modules.py | 2 +- modules.py | 307 ++++++++++++++++++++++++++++++++++ tools/infer/train-index-v2.py | 2 +- tools/rvc_for_realtime.py | 6 +- 8 files changed, 321 insertions(+), 14 deletions(-) create mode 100644 modules.py diff --git a/infer-web.py b/infer-web.py index 0225d4b..542b42b 100644 --- a/infer-web.py +++ b/infer-web.py @@ -389,14 +389,14 @@ def get_pretrained_models(path_str, f0_str, sr2): "assets/pretrained%s/%sD%s.pth" % (path_str, f0_str, sr2), os.F_OK ) if not if_pretrained_generator_exist: - logger.warn( + logger.warning( "assets/pretrained%s/%sG%s.pth not exist, will not use pretrained model", path_str, f0_str, sr2, ) if not if_pretrained_discriminator_exist: - logger.warn( + logger.warning( "assets/pretrained%s/%sD%s.pth not exist, will not use pretrained model", path_str, f0_str, diff --git a/infer/lib/train/data_utils.py b/infer/lib/train/data_utils.py index 7567970..1e1d1db 100644 --- a/infer/lib/train/data_utils.py +++ b/infer/lib/train/data_utils.py @@ -113,7 +113,7 @@ class TextAudioLoaderMultiNSFsid(torch.utils.data.Dataset): try: spec = torch.load(spec_filename) except: - logger.warn("%s %s", spec_filename, traceback.format_exc()) + logger.warning("%s %s", spec_filename, traceback.format_exc()) spec = spectrogram_torch( audio_norm, self.filter_length, @@ -305,7 +305,7 @@ class TextAudioLoader(torch.utils.data.Dataset): try: spec = torch.load(spec_filename) except: - logger.warn("%s %s", spec_filename, traceback.format_exc()) + logger.warning("%s %s", spec_filename, traceback.format_exc()) spec = spectrogram_torch( audio_norm, self.filter_length, diff --git a/infer/lib/train/utils.py b/infer/lib/train/utils.py index e26b608..c411c9b 100644 --- a/infer/lib/train/utils.py +++ b/infer/lib/train/utils.py @@ -33,7 +33,7 @@ def load_checkpoint_d(checkpoint_path, combd, sbd, optimizer=None, load_opt=1): try: new_state_dict[k] = saved_state_dict[k] if saved_state_dict[k].shape != state_dict[k].shape: - logger.warn( + logger.warning( "shape-%s-mismatch. need: %s, get: %s", k, state_dict[k].shape, @@ -111,7 +111,7 @@ def load_checkpoint(checkpoint_path, model, optimizer=None, load_opt=1): try: new_state_dict[k] = saved_state_dict[k] if saved_state_dict[k].shape != state_dict[k].shape: - logger.warn( + logger.warning( "shape-%s-mismatch|need-%s|get-%s", k, state_dict[k].shape, @@ -409,7 +409,7 @@ def get_hparams_from_file(config_path): def check_git_hash(model_dir): source_dir = os.path.dirname(os.path.realpath(__file__)) if not os.path.exists(os.path.join(source_dir, ".git")): - logger.warn( + logger.warning( "{} is not a git repository, therefore hash value comparison will be ignored.".format( source_dir ) @@ -422,7 +422,7 @@ def check_git_hash(model_dir): if os.path.exists(path): saved_hash = open(path).read() if saved_hash != cur_hash: - logger.warn( + logger.warning( "git hash values are different. {}(saved) != {}(current)".format( saved_hash[:8], cur_hash[:8] ) diff --git a/infer/modules/train/train.py b/infer/modules/train/train.py index eb457d4..763ad06 100644 --- a/infer/modules/train/train.py +++ b/infer/modules/train/train.py @@ -99,7 +99,7 @@ def main(): n_gpus = 1 if n_gpus < 1: # patch to unblock people without gpus. there is probably a better way. - logger.warn("NO GPU DETECTED: falling back to CPU - this may take a while") + logger.warning("NO GPU DETECTED: falling back to CPU - this may take a while") n_gpus = 1 os.environ["MASTER_ADDR"] = "localhost" os.environ["MASTER_PORT"] = str(randint(20000, 55555)) diff --git a/infer/modules/vc/modules.py b/infer/modules/vc/modules.py index 306149f..d90379b 100644 --- a/infer/modules/vc/modules.py +++ b/infer/modules/vc/modules.py @@ -224,7 +224,7 @@ class VC: ) except: info = traceback.format_exc() - logger.warn(info) + logger.warning(info) return info, (None, None) def vc_multi( diff --git a/modules.py b/modules.py new file mode 100644 index 0000000..d90379b --- /dev/null +++ b/modules.py @@ -0,0 +1,307 @@ +import traceback +import logging + +logger = logging.getLogger(__name__) + +import numpy as np +import soundfile as sf +import torch +from io import BytesIO + +from infer.lib.audio import load_audio, wav2 +from infer.lib.infer_pack.models import ( + SynthesizerTrnMs256NSFsid, + SynthesizerTrnMs256NSFsid_nono, + SynthesizerTrnMs768NSFsid, + SynthesizerTrnMs768NSFsid_nono, +) +from infer.modules.vc.pipeline import Pipeline +from infer.modules.vc.utils import * + + +class VC: + def __init__(self, config): + self.n_spk = None + self.tgt_sr = None + self.net_g = None + self.pipeline = None + self.cpt = None + self.version = None + self.if_f0 = None + self.version = None + self.hubert_model = None + + self.config = config + + def get_vc(self, sid, *to_return_protect): + logger.info("Get sid: " + sid) + + to_return_protect0 = { + "visible": self.if_f0 != 0, + "value": to_return_protect[0] + if self.if_f0 != 0 and to_return_protect + else 0.5, + "__type__": "update", + } + to_return_protect1 = { + "visible": self.if_f0 != 0, + "value": to_return_protect[1] + if self.if_f0 != 0 and to_return_protect + else 0.33, + "__type__": "update", + } + + if sid == "" or sid == []: + if self.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 + logger.info("Clean model cache") + del ( + self.net_g, + self.n_spk, + self.vc, + self.hubert_model, + self.tgt_sr, + ) # ,cpt + self.hubert_model = ( + self.net_g + ) = self.n_spk = self.vc = self.hubert_model = self.tgt_sr = None + if torch.cuda.is_available(): + torch.cuda.empty_cache() + ###楼下不这么折腾清理不干净 + self.if_f0 = self.cpt.get("f0", 1) + self.version = self.cpt.get("version", "v1") + if self.version == "v1": + if self.if_f0 == 1: + self.net_g = SynthesizerTrnMs256NSFsid( + *self.cpt["config"], is_half=self.config.is_half + ) + else: + self.net_g = SynthesizerTrnMs256NSFsid_nono(*self.cpt["config"]) + elif self.version == "v2": + if self.if_f0 == 1: + self.net_g = SynthesizerTrnMs768NSFsid( + *self.cpt["config"], is_half=self.config.is_half + ) + else: + self.net_g = SynthesizerTrnMs768NSFsid_nono(*self.cpt["config"]) + del self.net_g, self.cpt + if torch.cuda.is_available(): + torch.cuda.empty_cache() + return ( + {"visible": False, "__type__": "update"}, + { + "visible": True, + "value": to_return_protect0, + "__type__": "update", + }, + { + "visible": True, + "value": to_return_protect1, + "__type__": "update", + }, + "", + "", + ) + person = f'{os.getenv("weight_root")}/{sid}' + logger.info(f"Loading: {person}") + + self.cpt = torch.load(person, map_location="cpu") + self.tgt_sr = self.cpt["config"][-1] + self.cpt["config"][-3] = self.cpt["weight"]["emb_g.weight"].shape[0] # n_spk + self.if_f0 = self.cpt.get("f0", 1) + self.version = self.cpt.get("version", "v1") + + synthesizer_class = { + ("v1", 1): SynthesizerTrnMs256NSFsid, + ("v1", 0): SynthesizerTrnMs256NSFsid_nono, + ("v2", 1): SynthesizerTrnMs768NSFsid, + ("v2", 0): SynthesizerTrnMs768NSFsid_nono, + } + + self.net_g = synthesizer_class.get( + (self.version, self.if_f0), SynthesizerTrnMs256NSFsid + )(*self.cpt["config"], is_half=self.config.is_half) + + del self.net_g.enc_q + + self.net_g.load_state_dict(self.cpt["weight"], strict=False) + self.net_g.eval().to(self.config.device) + if self.config.is_half: + self.net_g = self.net_g.half() + else: + self.net_g = self.net_g.float() + + self.pipeline = Pipeline(self.tgt_sr, self.config) + n_spk = self.cpt["config"][-3] + index = {"value": get_index_path_from_model(sid), "__type__": "update"} + logger.info("Select index: " + index["value"]) + + return ( + ( + {"visible": True, "maximum": n_spk, "__type__": "update"}, + to_return_protect0, + to_return_protect1, + index, + index, + ) + if to_return_protect + else {"visible": True, "maximum": n_spk, "__type__": "update"} + ) + + def vc_single( + self, + sid, + input_audio_path, + f0_up_key, + f0_file, + f0_method, + file_index, + file_index2, + index_rate, + filter_radius, + resample_sr, + rms_mix_rate, + protect, + ): + 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 self.hubert_model is None: + self.hubert_model = load_hubert(self.config) + + 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 + + audio_opt = self.pipeline.pipeline( + self.hubert_model, + self.net_g, + sid, + audio, + input_audio_path, + times, + f0_up_key, + f0_method, + file_index, + index_rate, + self.if_f0, + filter_radius, + self.tgt_sr, + resample_sr, + rms_mix_rate, + self.version, + protect, + f0_file, + ) + if self.tgt_sr != resample_sr >= 16000: + tgt_sr = resample_sr + else: + tgt_sr = self.tgt_sr + index_info = ( + "Index:\n%s." % file_index + if os.path.exists(file_index) + else "Index not used." + ) + return ( + "Success.\n%s\nTime:\nnpy: %.2fs, f0: %.2fs, infer: %.2fs." + % (index_info, *times), + (tgt_sr, audio_opt), + ) + except: + info = traceback.format_exc() + logger.warning(info) + return info, (None, None) + + def vc_multi( + self, + sid, + dir_path, + opt_root, + paths, + f0_up_key, + f0_method, + file_index, + file_index2, + index_rate, + filter_radius, + resample_sr, + rms_mix_rate, + protect, + format1, + ): + try: + dir_path = ( + dir_path.strip(" ").strip('"').strip("\n").strip('"').strip(" ") + ) # 防止小白拷路径头尾带了空格和"和回车 + opt_root = opt_root.strip(" ").strip('"').strip("\n").strip('"').strip(" ") + os.makedirs(opt_root, exist_ok=True) + try: + if dir_path != "": + paths = [ + os.path.join(dir_path, name) for name in os.listdir(dir_path) + ] + else: + paths = [path.name for path in paths] + except: + traceback.print_exc() + paths = [path.name for path in paths] + infos = [] + for path in paths: + info, opt = self.vc_single( + sid, + path, + f0_up_key, + None, + f0_method, + file_index, + file_index2, + # file_big_npy, + index_rate, + filter_radius, + resample_sr, + rms_mix_rate, + protect, + ) + if "Success" in info: + try: + tgt_sr, audio_opt = opt + if format1 in ["wav", "flac"]: + sf.write( + "%s/%s.%s" + % (opt_root, os.path.basename(path), format1), + audio_opt, + tgt_sr, + ) + else: + path = "%s/%s.%s" % ( + opt_root, + os.path.basename(path), + format1, + ) + with BytesIO() as wavf: + sf.write(wavf, audio_opt, tgt_sr, format="wav") + wavf.seek(0, 0) + with open(path, "wb") as outf: + wav2(wavf, outf, format1) + except: + info += traceback.format_exc() + infos.append("%s->%s" % (os.path.basename(path), info)) + yield "\n".join(infos) + yield "\n".join(infos) + except: + yield traceback.format_exc() diff --git a/tools/infer/train-index-v2.py b/tools/infer/train-index-v2.py index 0efef7c..70f90a8 100644 --- a/tools/infer/train-index-v2.py +++ b/tools/infer/train-index-v2.py @@ -46,7 +46,7 @@ if big_npy.shape[0] > 2e5: ) except: info = traceback.format_exc() - logger.warn(info) + logger.warning(info) np.save("tools/infer/big_src_feature_mi.npy", big_npy) diff --git a/tools/rvc_for_realtime.py b/tools/rvc_for_realtime.py index a24f61d..094e307 100644 --- a/tools/rvc_for_realtime.py +++ b/tools/rvc_for_realtime.py @@ -140,7 +140,7 @@ class RVC: if last_rvc is not None and hasattr(last_rvc, "model_rmvpe"): self.model_rmvpe = last_rvc.model_rmvpe except: - logger.warn(traceback.format_exc()) + logger.warning(traceback.format_exc()) def change_key(self, new_key): self.f0_up_key = new_key @@ -326,10 +326,10 @@ class RVC: + (1 - self.index_rate) * feats[0][-leng_replace_head:] ) else: - logger.warn("Index search FAILED or disabled") + logger.warning("Index search FAILED or disabled") except: traceback.print_exc() - logger.warn("Index search FAILED") + logger.warning("Index search FAILED") feats = F.interpolate(feats.permute(0, 2, 1), scale_factor=2).permute(0, 2, 1) t3 = ttime() if self.if_f0 == 1: