tuna2134/sbv2-v2
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

Improve: Make ONNX inference tests more rigorous

Browse Source
This commit is contained in:
tsukumi
2024-09-23 12:27:29 +09:00
parent 2cdb5844cb
commit c792bf9a0d
4 changed files with 42 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
style_bert_vits2/nlp/chinese/bert_feature.py
View File

@@ -1,6 +1,6 @@
from __future__ import annotations
from typing import TYPE_CHECKING, Any, cast, Optional, Sequence, Union
from typing import TYPE_CHECKING, Any, Optional, Sequence, Union, cast
import numpy as np
from numpy.typing import NDArray
@@ -108,9 +108,9 @@ def extract_bert_feature_onnx(
res = session.run(
[output_name],
{
"input_ids": cast(NDArray[Any], inputs["input_ids"]).astype(np.int64),
"token_type_ids": cast(NDArray[Any], inputs["token_type_ids"]).astype(np.int64),
"attention_mask": cast(NDArray[Any], inputs["attention_mask"]).astype(np.int64),
"input_ids": inputs["input_ids"].astype(np.int64), # type: ignore
"token_type_ids": inputs["token_type_ids"].astype(np.int64), # type: ignore
"attention_mask": inputs["attention_mask"].astype(np.int64), # type: ignore
},
)[0]
@@ -120,9 +120,9 @@ def extract_bert_feature_onnx(
style_res = session.run(
[output_name],
{
"input_ids": cast(NDArray[Any], style_inputs["input_ids"]).astype(np.int64),
"token_type_ids": cast(NDArray[Any], style_inputs["token_type_ids"]).astype(np.int64),
"attention_mask": cast(NDArray[Any], style_inputs["attention_mask"]).astype(np.int64),
"input_ids": style_inputs["input_ids"].astype(np.int64), # type: ignore
"token_type_ids": style_inputs["token_type_ids"].astype(np.int64), # type: ignore
"attention_mask": style_inputs["attention_mask"].astype(np.int64), # type: ignore
},
)[0]
style_res_mean = np.mean(style_res, axis=0)

10
style_bert_vits2/nlp/english/bert_feature.py
View File

@@ -1,6 +1,6 @@
from __future__ import annotations
from typing import TYPE_CHECKING, Any, cast, Optional, Sequence, Union
from typing import TYPE_CHECKING, Any, Optional, Sequence, Union, cast
import numpy as np
from numpy.typing import NDArray
@@ -108,8 +108,8 @@ def extract_bert_feature_onnx(
res = session.run(
[output_name],
{
"input_ids": cast(NDArray[Any], inputs["input_ids"]).astype(np.int64),
"attention_mask": cast(NDArray[Any], inputs["attention_mask"]).astype(np.int64),
"input_ids": inputs["input_ids"].astype(np.int64), # type: ignore
"attention_mask": inputs["attention_mask"].astype(np.int64), # type: ignore
},
)[0]
@@ -119,8 +119,8 @@ def extract_bert_feature_onnx(
style_res = session.run(
[output_name],
{
"input_ids": cast(NDArray[Any], style_inputs["input_ids"]).astype(np.int64),
"attention_mask": cast(NDArray[Any], style_inputs["attention_mask"]).astype(np.int64),
"input_ids": style_inputs["input_ids"].astype(np.int64), # type: ignore
"attention_mask": style_inputs["attention_mask"].astype(np.int64), # type: ignore
},
)[0]
style_res_mean = np.mean(style_res, axis=0)

10
style_bert_vits2/nlp/japanese/bert_feature.py
View File

@@ -1,6 +1,6 @@
from __future__ import annotations
from typing import TYPE_CHECKING, Any, cast, Optional, Sequence, Union
from typing import TYPE_CHECKING, Any, Optional, Sequence, Union, cast
import numpy as np
from numpy.typing import NDArray
@@ -121,8 +121,8 @@ def extract_bert_feature_onnx(
res = session.run(
[output_name],
{
"input_ids": cast(NDArray[Any], inputs["input_ids"]).astype(np.int64),
"attention_mask": cast(NDArray[Any], inputs["attention_mask"]).astype(np.int64),
"input_ids": inputs["input_ids"].astype(np.int64), # type: ignore
"attention_mask": inputs["attention_mask"].astype(np.int64), # type: ignore
},
)[0]
@@ -132,8 +132,8 @@ def extract_bert_feature_onnx(
style_res = session.run(
[output_name],
{
"input_ids": cast(NDArray[Any], style_inputs["input_ids"]).astype(np.int64),
"attention_mask": cast(NDArray[Any], style_inputs["attention_mask"]).astype(np.int64),
"input_ids": style_inputs["input_ids"].astype(np.int64), # type: ignore
"attention_mask": style_inputs["attention_mask"].astype(np.int64), # type: ignore
},
)[0]
style_res_mean = np.mean(style_res, axis=0)

33
tests/test_main.py
View File

@@ -1,4 +1,4 @@
from typing import Any, Literal, Sequence, Union
from typing import Any, Literal, Sequence
import pytest
from scipy.io import wavfile
@@ -10,8 +10,8 @@ from style_bert_vits2.tts_model import TTSModelHolder
def synthesize(
inference_type: Literal["torch", "onnx"] = "torch",
device: str = "cpu",
onnx_providers: Sequence[Union[str, tuple[str, dict[str, Any]]]] = [
"CPUExecutionProvider"
onnx_providers: Sequence[tuple[str, dict[str, Any]]] = [
("CPUExecutionProvider", {}),
],
):
@@ -45,6 +45,11 @@ def synthesize(
model = model_holder.get_model(model_info.name, model_files[0])
model.load()
# ロードされた InferenceSession の ExecutionProvider が一致するか確認
# 一致しない場合、指定された ExecutionProvider で推論できない状態
assert model.onnx_session is not None
assert model.onnx_session.get_providers()[0] == onnx_providers[0][0]
# すべてのスタイルに対して音声合成を実行
for style in model_info.styles:
@@ -87,23 +92,35 @@ def test_synthesize_cpu():
def test_synthesize_cuda():
pytest.importorskip("torch.cuda")
synthesize(inference_type="torch", device="cuda")
def test_synthesize_onnx_cpu():
synthesize(inference_type="onnx", onnx_providers=["CPUExecutionProvider"])
synthesize(
inference_type="onnx",
onnx_providers=[
("CPUExecutionProvider", {}),
],
)
def test_synthesize_onnx_cuda():
synthesize(
inference_type="onnx",
onnx_providers=[
("CUDAExecutionProvider", {"cudnn_conv_algo_search": "DEFAULT"})
("CUDAExecutionProvider", {"cudnn_conv_algo_search": "DEFAULT"}),
],
)
def test_synthesize_onnx_directml():
pytest.importorskip("onnxruntime_directml")
synthesize(inference_type="onnx", onnx_providers=["DmlExecutionProvider"])
synthesize(
inference_type="onnx",
onnx_providers=[
# device_id: 0 は、システムにインストールされているプライマリディスプレイ用 GPU に対応する
# プライマリディスプレイ用 GPU (GPU 0) よりも性能の高い GPU が接続されている環境では、
# 適宜 device_id を変更する必要がある
# ref: https://github.com/w-okada/voice-changer/issues/410#issuecomment-1627994911
("DmlExecutionProvider", {"device_id": 0}),
],
)