Add voices pickle file

compute.py

@@ -0,0 +1,138 @@
+from cached_path import cached_path
+
+# from dp.phonemizer import Phonemizer
+print("NLTK")
+import nltk
+nltk.download('punkt')
+print("SCIPY")
+from scipy.io.wavfile import write
+print("TORCH STUFF")
+import torch
+print("START")
+torch.manual_seed(0)
+torch.backends.cudnn.benchmark = False
+torch.backends.cudnn.deterministic = True
+
+import random
+random.seed(0)
+
+import numpy as np
+np.random.seed(0)
+
+# load packages
+import time
+import random
+import yaml
+from munch import Munch
+import numpy as np
+import torch
+from torch import nn
+import torch.nn.functional as F
+import torchaudio
+import librosa
+from nltk.tokenize import word_tokenize
+
+from models import *
+from utils import *
+from text_utils import TextCleaner
+textclenaer = TextCleaner()
+
+
+to_mel = torchaudio.transforms.MelSpectrogram(
+    n_mels=80, n_fft=2048, win_length=1200, hop_length=300)
+mean, std = -4, 4
+
+def length_to_mask(lengths):
+    mask = torch.arange(lengths.max()).unsqueeze(0).expand(lengths.shape[0], -1).type_as(lengths)
+    mask = torch.gt(mask+1, lengths.unsqueeze(1))
+    return mask
+
+def preprocess(wave):
+    wave_tensor = torch.from_numpy(wave).float()
+    mel_tensor = to_mel(wave_tensor)
+    mel_tensor = (torch.log(1e-5 + mel_tensor.unsqueeze(0)) - mean) / std
+    return mel_tensor
+
+def compute_style(path):
+    wave, sr = librosa.load(path, sr=24000)
+    audio, index = librosa.effects.trim(wave, top_db=30)
+    if sr != 24000:
+        audio = librosa.resample(audio, sr, 24000)
+    mel_tensor = preprocess(audio).to(device)
+
+    with torch.no_grad():
+        ref_s = model.style_encoder(mel_tensor.unsqueeze(1))
+        ref_p = model.predictor_encoder(mel_tensor.unsqueeze(1))
+
+    return torch.cat([ref_s, ref_p], dim=1)
+
+device = 'cpu'
+if torch.cuda.is_available():
+    device = 'cuda'
+elif torch.backends.mps.is_available():
+    print("MPS would be available but cannot be used rn")
+    # device = 'mps'
+
+
+
+# config = yaml.safe_load(open("Models/LibriTTS/config.yml"))
+config = yaml.safe_load(open(str(cached_path("hf://yl4579/StyleTTS2-LibriTTS/Models/LibriTTS/config.yml"))))
+
+# load pretrained ASR model
+ASR_config = config.get('ASR_config', False)
+ASR_path = config.get('ASR_path', False)
+text_aligner = load_ASR_models(ASR_path, ASR_config)
+
+# load pretrained F0 model
+F0_path = config.get('F0_path', False)
+pitch_extractor = load_F0_models(F0_path)
+
+# load BERT model
+from Utils.PLBERT.util import load_plbert
+BERT_path = config.get('PLBERT_dir', False)
+plbert = load_plbert(BERT_path)
+
+model_params = recursive_munch(config['model_params'])
+model = build_model(model_params, text_aligner, pitch_extractor, plbert)
+_ = [model[key].eval() for key in model]
+_ = [model[key].to(device) for key in model]
+
+# params_whole = torch.load("Models/LibriTTS/epochs_2nd_00020.pth", map_location='cpu')
+params_whole = torch.load(str(cached_path("hf://yl4579/StyleTTS2-LibriTTS/Models/LibriTTS/epochs_2nd_00020.pth")), map_location='cpu')
+params = params_whole['net']
+
+for key in model:
+    if key in params:
+        print('%s loaded' % key)
+        try:
+            model[key].load_state_dict(params[key])
+        except:
+            from collections import OrderedDict
+            state_dict = params[key]
+            new_state_dict = OrderedDict()
+            for k, v in state_dict.items():
+                name = k[7:] # remove `module.`
+                new_state_dict[name] = v
+            # load params
+            model[key].load_state_dict(new_state_dict, strict=False)
+#             except:
+#                 _load(params[key], model[key])
+_ = [model[key].eval() for key in model]
+
+from Modules.diffusion.sampler import DiffusionSampler, ADPM2Sampler, KarrasSchedule
+
+sampler = DiffusionSampler(
+    model.diffusion.diffusion,
+    sampler=ADPM2Sampler(),
+    sigma_schedule=KarrasSchedule(sigma_min=0.0001, sigma_max=3.0, rho=9.0), # empirical parameters
+    clamp=False
+)
+voicelist = ['f-us-1', 'f-us-2', 'f-us-3', 'f-us-4', 'm-us-1', 'm-us-2', 'm-us-3', 'm-us-4']
+voices = {}
+# todo: cache computed style, load using pickle
+for v in voicelist:
+    print(f"Loading voice {v}")
+    voices[v] = compute_style(f'voices/{v}.wav')
+import pickle
+with open('voices.pkl', 'wb') as f:
+    pickle.dump(voices, f)

voices.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58e11e1d6726c8992f5325aca8b381ad37facbd7380ebb5f5e04d77a017b4ee3
+size 10739