Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

追加：AudioQuery.pauseLengthのSkipJsonSchemaをなくす #1430

Merged
merged 4 commits into from
Jun 26, 2024
Merged

追加：AudioQuery.pauseLengthのSkipJsonSchemaをなくす #1430

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
b17a0df
pauseLengthのSkipJsonSchemaをなくす
Hiroshiba Jun 24, 2024
d7fb9fc
nullのときの処理を追加
Hiroshiba Jun 25, 2024
23fa9f2
デフォルト値追記
Hiroshiba Jun 25, 2024
f2de31c
python -m pytest --snapshot-update
Hiroshiba Jun 25, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 10 additions & 3 deletions test/e2e/__snapshots__/test_openapi/test_OpenAPIの形が変わっていないことを確認.json
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

3 changes: 3 additions & 0 deletions test/e2e/single_api/tts_pipeline/__snapshots__/test_synthesis.ambr
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,3 +2,6 @@
# name: test_post_synthesis_200
'MD5:f7d42ce5787856549abc3d2d7561c06f'
# ---
# name: test_post_synthesis_old_audio_query_200
'MD5:f7d42ce5787856549abc3d2d7561c06f'
# ---
34 changes: 34 additions & 0 deletions test/e2e/single_api/tts_pipeline/test_synthesis.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,3 +41,37 @@ def test_post_synthesis_200(client: TestClient, snapshot: SnapshotAssertion) ->
# 音声波形が一致する
assert response.headers["content-type"] == "audio/wav"
assert snapshot == hash_wave_floats_from_wav_bytes(response.read())


def test_post_synthesis_old_audio_query_200(
client: TestClient, snapshot: SnapshotAssertion
) -> None:
"""古いバージョンの audio_query でもエラーなく合成できる"""
query = {
"accent_phrases": [
{
"moras": [
gen_mora("テ", "t", 2.3, "e", 0.8, 3.3),
gen_mora("ス", "s", 2.1, "U", 0.3, 0.0),
gen_mora("ト", "t", 2.3, "o", 1.8, 4.1),
],
"accent": 1,
"pause_mora": None,
"is_interrogative": False,
}
],
"speedScale": 1.0,
"pitchScale": 1.0,
"intonationScale": 1.0,
"volumeScale": 1.0,
"prePhonemeLength": 0.1,
"postPhonemeLength": 0.1,
"outputSamplingRate": 24000,
"outputStereo": False,
}
response = client.post("/synthesis", params={"speaker": 0}, json=query)
assert response.status_code == 200

# 音声波形が一致する
assert response.headers["content-type"] == "audio/wav"
assert snapshot == hash_wave_floats_from_wav_bytes(response.read())
9 changes: 6 additions & 3 deletions voicevox_engine/model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,10 +25,13 @@ class AudioQuery(BaseModel):
volumeScale: float = Field(title="全体の音量")
prePhonemeLength: float = Field(title="音声の前の無音時間")
postPhonemeLength: float = Field(title="音声の後の無音時間")
pauseLength: float | SkipJsonSchema[None] = Field(
default=None, title="句読点などの無音時間"
pauseLength: float | None = Field(
default=None,
title="句読点などの無音時間。nullのときは無視される。デフォルト値はnull",
)
pauseLengthScale: float = Field(
default=1, title="句読点などの無音時間（倍率）。デフォルト値は1"
)
pauseLengthScale: float = Field(default=1, title="句読点などの無音時間（倍率）")
outputSamplingRate: int = Field(title="音声データの出力サンプリングレート")
outputStereo: bool = Field(title="音声データをステレオ出力するか否か")
kana: str | SkipJsonSchema[None] = Field(
Expand Down
Loading