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
38
infer.py
38
infer.py
@@ -11,11 +11,14 @@
|
||||
import torch
|
||||
import commons
|
||||
from text import cleaned_text_to_sequence, get_bert
|
||||
from emo_gen import get_emo
|
||||
from text.cleaner import clean_text
|
||||
import utils
|
||||
|
||||
from models import SynthesizerTrn
|
||||
from text.symbols import symbols
|
||||
from oldVersion.V200.models import SynthesizerTrn as V200SynthesizerTrn
|
||||
from oldVersion.V200.text import symbols as V200symbols
|
||||
from oldVersion.V111.models import SynthesizerTrn as V111SynthesizerTrn
|
||||
from oldVersion.V111.text import symbols as V111symbols
|
||||
from oldVersion.V110.models import SynthesizerTrn as V110SynthesizerTrn
|
||||
@@ -23,13 +26,16 @@ from oldVersion.V110.text import symbols as V110symbols
|
||||
from oldVersion.V101.models import SynthesizerTrn as V101SynthesizerTrn
|
||||
from oldVersion.V101.text import symbols as V101symbols
|
||||
|
||||
from oldVersion import V111, V110, V101
|
||||
from oldVersion import V111, V110, V101, V200
|
||||
|
||||
# 当前版本信息
|
||||
latest_version = "2.0"
|
||||
latest_version = "2.1"
|
||||
|
||||
# 版本兼容
|
||||
SynthesizerTrnMap = {
|
||||
"2.0.2-fix": V200SynthesizerTrn,
|
||||
"2.0.1": V200SynthesizerTrn,
|
||||
"2.0": V200SynthesizerTrn,
|
||||
"1.1.1-fix": V111SynthesizerTrn,
|
||||
"1.1.1": V111SynthesizerTrn,
|
||||
"1.1": V110SynthesizerTrn,
|
||||
@@ -40,6 +46,9 @@ SynthesizerTrnMap = {
|
||||
}
|
||||
|
||||
symbolsMap = {
|
||||
"2.0.2-fix": V200symbols,
|
||||
"2.0.1": V200symbols,
|
||||
"2.0": V200symbols,
|
||||
"1.1.1-fix": V111symbols,
|
||||
"1.1.1": V111symbols,
|
||||
"1.1": V110symbols,
|
||||
@@ -73,7 +82,7 @@ def get_net_g(model_path: str, version: str, device: str, hps):
|
||||
return net_g
|
||||
|
||||
|
||||
def get_text(text, language_str, hps, device):
|
||||
def get_text(text, reference_audio, emotion, language_str, hps, device):
|
||||
# 在此处实现当前版本的get_text
|
||||
norm_text, phone, tone, word2ph = clean_text(text, language_str)
|
||||
phone, tone, language = cleaned_text_to_sequence(phone, tone, language_str)
|
||||
@@ -104,6 +113,12 @@ def get_text(text, language_str, hps, device):
|
||||
else:
|
||||
raise ValueError("language_str should be ZH, JP or EN")
|
||||
|
||||
emo = (
|
||||
torch.from_numpy(get_emo(reference_audio))
|
||||
if reference_audio
|
||||
else torch.Tensor([emotion])
|
||||
)
|
||||
|
||||
assert bert.shape[-1] == len(
|
||||
phone
|
||||
), f"Bert seq len {bert.shape[-1]} != {len(phone)}"
|
||||
@@ -111,7 +126,7 @@ def get_text(text, language_str, hps, device):
|
||||
phone = torch.LongTensor(phone)
|
||||
tone = torch.LongTensor(tone)
|
||||
language = torch.LongTensor(language)
|
||||
return bert, ja_bert, en_bert, phone, tone, language
|
||||
return bert, ja_bert, en_bert, emo, phone, tone, language
|
||||
|
||||
|
||||
def infer(
|
||||
@@ -125,11 +140,16 @@ def infer(
|
||||
hps,
|
||||
net_g,
|
||||
device,
|
||||
reference_audio=None,
|
||||
emotion=None,
|
||||
skip_start=False,
|
||||
skip_end=False,
|
||||
):
|
||||
# 支持中日双语版本
|
||||
# 支持中日英三语版本
|
||||
inferMap_V2 = {
|
||||
"2.0.2-fix": V200.infer,
|
||||
"2.0.1": V200.infer,
|
||||
"2.0": V200.infer,
|
||||
"1.1.1-fix": V111.infer_fix,
|
||||
"1.1.1": V111.infer,
|
||||
"1.1": V110.infer,
|
||||
@@ -171,8 +191,8 @@ def infer(
|
||||
device,
|
||||
)
|
||||
# 在此处实现当前版本的推理
|
||||
bert, ja_bert, en_bert, phones, tones, lang_ids = get_text(
|
||||
text, language, hps, device
|
||||
bert, ja_bert, en_bert, emo, phones, tones, lang_ids = get_text(
|
||||
text, reference_audio, emotion, language, hps, device
|
||||
)
|
||||
if skip_start:
|
||||
phones = phones[1:]
|
||||
@@ -285,6 +305,7 @@ def infer_multilang(
|
||||
bert = bert.to(device).unsqueeze(0)
|
||||
ja_bert = ja_bert.to(device).unsqueeze(0)
|
||||
en_bert = en_bert.to(device).unsqueeze(0)
|
||||
emo = emo.to(device).unsqueeze(0)
|
||||
x_tst_lengths = torch.LongTensor([phones.size(0)]).to(device)
|
||||
del phones
|
||||
speakers = torch.LongTensor([hps.data.spk2id[sid]]).to(device)
|
||||
@@ -298,6 +319,7 @@ def infer_multilang(
|
||||
bert,
|
||||
ja_bert,
|
||||
en_bert,
|
||||
emo,
|
||||
sdp_ratio=sdp_ratio,
|
||||
noise_scale=noise_scale,
|
||||
noise_scale_w=noise_scale_w,
|
||||
@@ -307,7 +329,7 @@ def infer_multilang(
|
||||
.float()
|
||||
.numpy()
|
||||
)
|
||||
del x_tst, tones, lang_ids, bert, x_tst_lengths, speakers, ja_bert, en_bert
|
||||
del x_tst, tones, lang_ids, bert, x_tst_lengths, speakers, ja_bert, en_bert, emo
|
||||
if torch.cuda.is_available():
|
||||
torch.cuda.empty_cache()
|
||||
return audio
|
||||
|
||||
Reference in New Issue
Block a user