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
@@ -176,6 +176,80 @@ if __name__ == "__main__":
|
||||
class Text(BaseModel):
|
||||
text: str
|
||||
|
||||
def _voice(
|
||||
text: str,
|
||||
model_id: int,
|
||||
speaker_name: str,
|
||||
speaker_id: int,
|
||||
sdp_ratio: float,
|
||||
noise: float,
|
||||
noisew: float,
|
||||
length: float,
|
||||
language: str,
|
||||
auto_translate: bool,
|
||||
auto_split: bool,
|
||||
) -> Response | Dict[str, any]:
|
||||
# 检查模型是否存在
|
||||
if model_id not in loaded_models.models.keys():
|
||||
return {"status": 10, "detail": f"模型model_id={model_id}未加载"}
|
||||
# 检查是否提供speaker
|
||||
if speaker_name is None and speaker_id is None:
|
||||
return {"status": 11, "detail": "请提供speaker_name或speaker_id"}
|
||||
elif speaker_name is None:
|
||||
# 检查speaker_id是否存在
|
||||
if speaker_id not in loaded_models.models[model_id].id2spk.keys():
|
||||
return {"status": 12, "detail": f"角色speaker_id={speaker_id}不存在"}
|
||||
speaker_name = loaded_models.models[model_id].id2spk[speaker_id]
|
||||
# 检查speaker_name是否存在
|
||||
if speaker_name not in loaded_models.models[model_id].spk2id.keys():
|
||||
return {"status": 13, "detail": f"角色speaker_name={speaker_name}不存在"}
|
||||
if language is None:
|
||||
language = loaded_models.models[model_id].language
|
||||
if auto_translate:
|
||||
text = trans.translate(Sentence=text, to_Language=language.lower())
|
||||
if not auto_split:
|
||||
with torch.no_grad():
|
||||
audio = infer(
|
||||
text=text,
|
||||
sdp_ratio=sdp_ratio,
|
||||
noise_scale=noise,
|
||||
noise_scale_w=noisew,
|
||||
length_scale=length,
|
||||
sid=speaker_name,
|
||||
language=language,
|
||||
hps=loaded_models.models[model_id].hps,
|
||||
net_g=loaded_models.models[model_id].net_g,
|
||||
device=loaded_models.models[model_id].device,
|
||||
)
|
||||
else:
|
||||
texts = cut_sent(text)
|
||||
audios = []
|
||||
with torch.no_grad():
|
||||
for t in texts:
|
||||
audios.append(
|
||||
infer(
|
||||
text=t,
|
||||
sdp_ratio=sdp_ratio,
|
||||
noise_scale=noise,
|
||||
noise_scale_w=noisew,
|
||||
length_scale=length,
|
||||
sid=speaker_name,
|
||||
language=language,
|
||||
hps=loaded_models.models[model_id].hps,
|
||||
net_g=loaded_models.models[model_id].net_g,
|
||||
device=loaded_models.models[model_id].device,
|
||||
)
|
||||
)
|
||||
audios.append(np.zeros(int(44100 * 0.2)))
|
||||
audio = np.concatenate(audios)
|
||||
audio = gradio.processing_utils.convert_to_16_bit_wav(audio)
|
||||
wavContent = BytesIO()
|
||||
wavfile.write(
|
||||
wavContent, loaded_models.models[model_id].hps.data.sampling_rate, audio
|
||||
)
|
||||
response = Response(content=wavContent.getvalue(), media_type="audio/wav")
|
||||
return response
|
||||
|
||||
@app.post("/voice")
|
||||
def voice(
|
||||
request: Request, # fastapi自动注入
|
||||
@@ -198,66 +272,19 @@ if __name__ == "__main__":
|
||||
logger.info(
|
||||
f"{request.client.host}:{request.client.port}/voice { unquote(str(request.query_params) )} text={text}"
|
||||
)
|
||||
# 检查模型是否存在
|
||||
if model_id not in loaded_models.models.keys():
|
||||
return {"status": 10, "detail": f"模型model_id={model_id}未加载"}
|
||||
# 检查是否提供speaker
|
||||
if speaker_name is None and speaker_id is None:
|
||||
return {"status": 11, "detail": "请提供speaker_name或speaker_id"}
|
||||
elif speaker_name is None:
|
||||
# 检查speaker_id是否存在
|
||||
if speaker_id not in loaded_models.models[model_id].id2spk.keys():
|
||||
return {"status": 12, "detail": f"角色speaker_id={speaker_id}不存在"}
|
||||
speaker_name = loaded_models.models[model_id].id2spk[speaker_id]
|
||||
# 检查speaker_name是否存在
|
||||
if speaker_name not in loaded_models.models[model_id].spk2id.keys():
|
||||
return {"status": 13, "detail": f"角色speaker_name={speaker_name}不存在"}
|
||||
if language is None:
|
||||
language = loaded_models.models[model_id].language
|
||||
if auto_translate:
|
||||
text = trans.translate(Sentence=text, to_Language=language.lower())
|
||||
if not auto_split:
|
||||
with torch.no_grad():
|
||||
audio = infer(
|
||||
text=text,
|
||||
sdp_ratio=sdp_ratio,
|
||||
noise_scale=noise,
|
||||
noise_scale_w=noisew,
|
||||
length_scale=length,
|
||||
sid=speaker_name,
|
||||
language=language,
|
||||
hps=loaded_models.models[model_id].hps,
|
||||
net_g=loaded_models.models[model_id].net_g,
|
||||
device=loaded_models.models[model_id].device,
|
||||
)
|
||||
else:
|
||||
texts = cut_sent(text)
|
||||
audios = []
|
||||
with torch.no_grad():
|
||||
for t in texts:
|
||||
audios.append(
|
||||
infer(
|
||||
text=t,
|
||||
sdp_ratio=sdp_ratio,
|
||||
noise_scale=noise,
|
||||
noise_scale_w=noisew,
|
||||
length_scale=length,
|
||||
sid=speaker_name,
|
||||
language=language,
|
||||
hps=loaded_models.models[model_id].hps,
|
||||
net_g=loaded_models.models[model_id].net_g,
|
||||
device=loaded_models.models[model_id].device,
|
||||
)
|
||||
)
|
||||
audios.append(np.zeros((int)(44100 * 0.3)))
|
||||
audio = np.concatenate(audios)
|
||||
audio = gradio.processing_utils.convert_to_16_bit_wav(audio)
|
||||
wavContent = BytesIO()
|
||||
wavfile.write(
|
||||
wavContent, loaded_models.models[model_id].hps.data.sampling_rate, audio
|
||||
return _voice(
|
||||
text=text,
|
||||
model_id=model_id,
|
||||
speaker_name=speaker_name,
|
||||
speaker_id=speaker_id,
|
||||
sdp_ratio=sdp_ratio,
|
||||
noise=noise,
|
||||
noisew=noisew,
|
||||
length=length,
|
||||
language=language,
|
||||
auto_translate=auto_translate,
|
||||
auto_split=auto_split,
|
||||
)
|
||||
response = Response(content=wavContent.getvalue(), media_type="audio/wav")
|
||||
return response
|
||||
|
||||
@app.get("/voice")
|
||||
def voice(
|
||||
@@ -280,66 +307,19 @@ if __name__ == "__main__":
|
||||
logger.info(
|
||||
f"{request.client.host}:{request.client.port}/voice { unquote(str(request.query_params) )}"
|
||||
)
|
||||
# 检查模型是否存在
|
||||
if model_id not in loaded_models.models.keys():
|
||||
return {"status": 10, "detail": f"模型model_id={model_id}未加载"}
|
||||
# 检查是否提供speaker
|
||||
if speaker_name is None and speaker_id is None:
|
||||
return {"status": 11, "detail": "请提供speaker_name或speaker_id"}
|
||||
elif speaker_name is None:
|
||||
# 检查speaker_id是否存在
|
||||
if speaker_id not in loaded_models.models[model_id].id2spk.keys():
|
||||
return {"status": 12, "detail": f"角色speaker_id={speaker_id}不存在"}
|
||||
speaker_name = loaded_models.models[model_id].id2spk[speaker_id]
|
||||
# 检查speaker_name是否存在
|
||||
if speaker_name not in loaded_models.models[model_id].spk2id.keys():
|
||||
return {"status": 13, "detail": f"角色speaker_name={speaker_name}不存在"}
|
||||
if language is None:
|
||||
language = loaded_models.models[model_id].language
|
||||
if auto_translate:
|
||||
text = trans.translate(Sentence=text, to_Language=language.lower())
|
||||
if not auto_split:
|
||||
with torch.no_grad():
|
||||
audio = infer(
|
||||
text=text,
|
||||
sdp_ratio=sdp_ratio,
|
||||
noise_scale=noise,
|
||||
noise_scale_w=noisew,
|
||||
length_scale=length,
|
||||
sid=speaker_name,
|
||||
language=language,
|
||||
hps=loaded_models.models[model_id].hps,
|
||||
net_g=loaded_models.models[model_id].net_g,
|
||||
device=loaded_models.models[model_id].device,
|
||||
)
|
||||
else:
|
||||
texts = cut_sent(text)
|
||||
audios = []
|
||||
with torch.no_grad():
|
||||
for t in texts:
|
||||
audios.append(
|
||||
infer(
|
||||
text=t,
|
||||
sdp_ratio=sdp_ratio,
|
||||
noise_scale=noise,
|
||||
noise_scale_w=noisew,
|
||||
length_scale=length,
|
||||
sid=speaker_name,
|
||||
language=language,
|
||||
hps=loaded_models.models[model_id].hps,
|
||||
net_g=loaded_models.models[model_id].net_g,
|
||||
device=loaded_models.models[model_id].device,
|
||||
)
|
||||
)
|
||||
audios.append(np.zeros((int)(44100 * 0.3)))
|
||||
audio = np.concatenate(audios)
|
||||
audio = gradio.processing_utils.convert_to_16_bit_wav(audio)
|
||||
wavContent = BytesIO()
|
||||
wavfile.write(
|
||||
wavContent, loaded_models.models[model_id].hps.data.sampling_rate, audio
|
||||
return _voice(
|
||||
text=text,
|
||||
model_id=model_id,
|
||||
speaker_name=speaker_name,
|
||||
speaker_id=speaker_id,
|
||||
sdp_ratio=sdp_ratio,
|
||||
noise=noise,
|
||||
noisew=noisew,
|
||||
length=length,
|
||||
language=language,
|
||||
auto_translate=auto_translate,
|
||||
auto_split=auto_split,
|
||||
)
|
||||
response = Response(content=wavContent.getvalue(), media_type="audio/wav")
|
||||
return response
|
||||
|
||||
@app.get("/models/info")
|
||||
def get_loaded_models_info(request: Request):
|
||||
|
||||
Reference in New Issue
Block a user