Dev emo (#171)
* SYNC CHANGE TO EMO BRANCH (#162) * Update README.md * 更新 bert_models.json * fix * Update data_utils.py * Update infer.py * performance improve * Feat: support auto split in webui (#158) * Feat: support auto split in webui * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Fix: change /voice api to post (#160) * Fix: change /voice api to post * Fix: support /voice api get * Fix: Add missing torch.cuda.empty_cache() (#161) --------- Co-authored-by: Sora <atri@suzakuintsubaki.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Artrajz <969242373@qq.com> * sync (#163) * Update README.md * 更新 bert_models.json * fix * Update data_utils.py * Update infer.py * performance improve * Feat: support auto split in webui (#158) * Feat: support auto split in webui * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Fix: change /voice api to post (#160) * Fix: change /voice api to post * Fix: support /voice api get * Fix: Add missing torch.cuda.empty_cache() (#161) * del emo * del emo * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: Sora <atri@suzakuintsubaki.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Artrajz <969242373@qq.com> * Add files via upload * Update infer.py * add emo * add emo * Update default_config.yml * Fix slice segments GPU perf (#165) * Fix slice segments GPU perf * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update commons.py --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Update infer.py * Update models.py * Update infer.py * remove spec cache * Update data_utils.py * Update data_utils.py * Update train_ms.py * Revert "Fix slice segments GPU perf (#165)" (#169) This reverts commit 28430fc76bc628297bb59d8f8d25100dbe46ab59. * Update train_ms.py * Update train_ms.py * Update data_utils.py * Update data_utils.py * Update train_ms.py * Update train_ms.py * Update train_ms.py * Update train_ms.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update default_config.yml * Switch to Japanese wwm DeBERTa (#172) * Switch to Japanese wwm DeBERTa * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Fix wrong ellipsis g2p (#173) * Switch to Japanese wwm DeBERTa * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fix ellipsis g2p * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Add files via upload * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fix English phones not aligned with BERT features (#174) * Fix English phones not aligned with BERT features * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Fix english bert gen (#175) * Update webui.py * Update webui.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * add NCCL timeout * Update train_ms.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update train_ms.py * Update default_config.yml * Update infer.py * Update models.py * Update train_ms.py * Update infer.py * Update emo_gen.py * Feat: Support load and infer 2.0 models (#178) * Feat: Support load and infer 2.0 models * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * 复用相同逻辑，修正静音添加错误 (#181) * Refactor: reuse the same part of voice api. * Fix: server_fastapi.py * Update train_ms.py * Update data_utils.py * Update data_utils.py * Update train_ms.py * Update train_ms.py * Update train_ms.py * Update train_ms.py * Update data_utils.py * Update data_utils.py * Add files via upload * Update train_ms.py * Update train_ms.py * Update train_ms.py * Update default_config.yml * Update utils.py * Update train_ms.py * Update utils.py * Update default_config.yml * Update data_utils.py * Update default_config.yml * Update train_ms.py * Update train_ms.py * Update config.py * Update utils.py * Update train_ms.py * Update train_ms.py * feat: add voice mix and tone mix (#187) * feat: add voice mix and tone mix * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Stardust·减 <star_dust_chen@foxmail.com> * Add files via upload * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: Sora <atri@suzakuintsubaki.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Artrajz <969242373@qq.com> Co-authored-by: Leng Yue <lengyue@lengyue.me> Co-authored-by: OedoSoldier <31711261+OedoSoldier@users.noreply.github.com> Co-authored-by: 潮幻Mark <sunyunfei201@gmail.com>
This commit is contained in:
Stardust·减
@@ -3,11 +3,13 @@ import random
|
||||
import torch
|
||||
import torch.utils.data
|
||||
from tqdm import tqdm
|
||||
import numpy as np
|
||||
from tools.log import logger
|
||||
import commons
|
||||
from mel_processing import spectrogram_torch, mel_spectrogram_torch
|
||||
from utils import load_wav_to_torch, load_filepaths_and_text
|
||||
from text import cleaned_text_to_sequence
|
||||
import config as config
|
||||
|
||||
"""Multi speaker version"""
|
||||
|
||||
@@ -40,7 +42,7 @@ class TextAudioSpeakerLoader(torch.utils.data.Dataset):
|
||||
|
||||
self.add_blank = hparams.add_blank
|
||||
self.min_text_len = getattr(hparams, "min_text_len", 1)
|
||||
self.max_text_len = getattr(hparams, "max_text_len", 300)
|
||||
self.max_text_len = getattr(hparams, "max_text_len", 384)
|
||||
|
||||
random.seed(1234)
|
||||
random.shuffle(self.audiopaths_sid_text)
|
||||
@@ -91,7 +93,8 @@ class TextAudioSpeakerLoader(torch.utils.data.Dataset):
|
||||
|
||||
spec, wav = self.get_audio(audiopath)
|
||||
sid = torch.LongTensor([int(self.spk_map[sid])])
|
||||
return (phones, spec, wav, sid, tone, language, bert, ja_bert, en_bert)
|
||||
emo = torch.FloatTensor(np.load(audiopath.replace(".wav", ".emo.npy")))
|
||||
return (phones, spec, wav, sid, tone, language, bert, ja_bert, en_bert, emo)
|
||||
|
||||
def get_audio(self, filename):
|
||||
audio, sampling_rate = load_wav_to_torch(filename)
|
||||
@@ -131,7 +134,8 @@ class TextAudioSpeakerLoader(torch.utils.data.Dataset):
|
||||
center=False,
|
||||
)
|
||||
spec = torch.squeeze(spec, 0)
|
||||
torch.save(spec, spec_filename)
|
||||
if config.train_ms.spec_cache:
|
||||
torch.save(spec, spec_filename)
|
||||
return spec, audio_norm
|
||||
|
||||
def get_text(self, text, word2ph, phone, tone, language_str, wav_path):
|
||||
@@ -211,6 +215,7 @@ class TextAudioSpeakerCollate:
|
||||
bert_padded = torch.FloatTensor(len(batch), 1024, max_text_len)
|
||||
ja_bert_padded = torch.FloatTensor(len(batch), 1024, max_text_len)
|
||||
en_bert_padded = torch.FloatTensor(len(batch), 1024, max_text_len)
|
||||
emo = torch.FloatTensor(len(batch), 1024)
|
||||
|
||||
spec_padded = torch.FloatTensor(len(batch), batch[0][1].size(0), max_spec_len)
|
||||
wav_padded = torch.FloatTensor(len(batch), 1, max_wav_len)
|
||||
@@ -222,6 +227,7 @@ class TextAudioSpeakerCollate:
|
||||
bert_padded.zero_()
|
||||
ja_bert_padded.zero_()
|
||||
en_bert_padded.zero_()
|
||||
emo.zero_()
|
||||
|
||||
for i in range(len(ids_sorted_decreasing)):
|
||||
row = batch[ids_sorted_decreasing[i]]
|
||||
@@ -255,6 +261,8 @@ class TextAudioSpeakerCollate:
|
||||
en_bert = row[8]
|
||||
en_bert_padded[i, :, : en_bert.size(1)] = en_bert
|
||||
|
||||
emo[i, :] = row[9]
|
||||
|
||||
return (
|
||||
text_padded,
|
||||
text_lengths,
|
||||
@@ -268,6 +276,7 @@ class TextAudioSpeakerCollate:
|
||||
bert_padded,
|
||||
ja_bert_padded,
|
||||
en_bert_padded,
|
||||
emo,
|
||||
)
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user