Speech calls keep one connection per server, opened when listening starts
transcribe and speak share an httpx client per speech server with a 300 s keep-alive, and run on the engine's loop. stt warms it with GET /v1/models when an utterance opens, so a reply's first sentence finds the connection open: a new one over a lossy link cost up to a second (openpanel V4).
This commit is contained in:
@@ -160,6 +160,26 @@ async def list_models(api_base: str, api_key: str, timeout: float = 15.0) -> lis
|
|||||||
return sorted(str(m["id"]) for m in data if isinstance(m, dict) and "id" in m)
|
return sorted(str(m["id"]) for m in data if isinstance(m, dict) and "id" in m)
|
||||||
|
|
||||||
|
|
||||||
|
#: One client per speech server, so its connection stays open between calls
|
||||||
|
#: (`parrot serve` keeps an idle one 600 s). A new connection over a lossy
|
||||||
|
#: link can cost a second, which a spoken reply cannot spare.
|
||||||
|
_speech: dict[str, httpx.AsyncClient] = {}
|
||||||
|
|
||||||
|
|
||||||
|
def _speech_client(api_base: str) -> httpx.AsyncClient:
|
||||||
|
"""The client for this speech server. Used from the engine's loop only."""
|
||||||
|
http = _speech.get(api_base)
|
||||||
|
if http is None:
|
||||||
|
limits = httpx.Limits(keepalive_expiry=300)
|
||||||
|
http = _speech[api_base] = httpx.AsyncClient(limits=limits)
|
||||||
|
return http
|
||||||
|
|
||||||
|
|
||||||
|
async def warm(api_base: str) -> None:
|
||||||
|
"""Open the connection to a speech server ahead of the call that needs it."""
|
||||||
|
await _speech_client(api_base).get(api_base.rstrip("/") + "/models", timeout=10)
|
||||||
|
|
||||||
|
|
||||||
async def transcribe(
|
async def transcribe(
|
||||||
api_base: str,
|
api_base: str,
|
||||||
audio: bytes,
|
audio: bytes,
|
||||||
@@ -170,12 +190,12 @@ async def transcribe(
|
|||||||
timeout: float = 30.0,
|
timeout: float = 30.0,
|
||||||
) -> str:
|
) -> str:
|
||||||
"""``POST {api_base}/audio/transcriptions``: a whole clip, and what it says."""
|
"""``POST {api_base}/audio/transcriptions``: a whole clip, and what it says."""
|
||||||
async with httpx.AsyncClient(timeout=timeout) as http:
|
response = await _speech_client(api_base).post(
|
||||||
response = await http.post(
|
api_base.rstrip("/") + "/audio/transcriptions",
|
||||||
api_base.rstrip("/") + "/audio/transcriptions",
|
files={"file": (filename, audio, media_type)},
|
||||||
files={"file": (filename, audio, media_type)},
|
data={"model": model, "response_format": "json"},
|
||||||
data={"model": model, "response_format": "json"},
|
timeout=timeout,
|
||||||
)
|
)
|
||||||
if response.is_error:
|
if response.is_error:
|
||||||
raise ProviderError(_detail(response))
|
raise ProviderError(_detail(response))
|
||||||
return str(response.json().get("text") or "")
|
return str(response.json().get("text") or "")
|
||||||
@@ -194,16 +214,11 @@ async def speak(
|
|||||||
MP3 rather than WAV: a seventh of the bytes, which over a slow link to
|
MP3 rather than WAV: a seventh of the bytes, which over a slow link to
|
||||||
the server is most of the wait for a sentence.
|
the server is most of the wait for a sentence.
|
||||||
"""
|
"""
|
||||||
async with httpx.AsyncClient(timeout=timeout) as http:
|
response = await _speech_client(api_base).post(
|
||||||
response = await http.post(
|
api_base.rstrip("/") + "/audio/speech",
|
||||||
api_base.rstrip("/") + "/audio/speech",
|
json={"model": model, "input": text, "voice": voice, "response_format": "mp3"},
|
||||||
json={
|
timeout=timeout,
|
||||||
"model": model,
|
)
|
||||||
"input": text,
|
|
||||||
"voice": voice,
|
|
||||||
"response_format": "mp3",
|
|
||||||
},
|
|
||||||
)
|
|
||||||
if response.is_error:
|
if response.is_error:
|
||||||
raise ProviderError(_detail(response))
|
raise ProviderError(_detail(response))
|
||||||
return response.content
|
return response.content
|
||||||
|
|||||||
@@ -9,6 +9,7 @@ it gets.
|
|||||||
from __future__ import annotations
|
from __future__ import annotations
|
||||||
|
|
||||||
import asyncio
|
import asyncio
|
||||||
|
import contextlib
|
||||||
import hashlib
|
import hashlib
|
||||||
import logging
|
import logging
|
||||||
import re
|
import re
|
||||||
@@ -128,6 +129,13 @@ class _Speech(Node):
|
|||||||
def _load(self, reference: dict[str, Any]) -> bytes:
|
def _load(self, reference: dict[str, Any]) -> bytes:
|
||||||
return b"".join(self._artifacts.read(str(reference["digest"])))
|
return b"".join(self._artifacts.read(str(reference["digest"])))
|
||||||
|
|
||||||
|
def _call(self, work: Coroutine[Any, Any, Any]) -> Future[Any]:
|
||||||
|
"""Run on the engine's loop, where the server's connection is kept."""
|
||||||
|
if self._loop is None:
|
||||||
|
work.close()
|
||||||
|
raise RuntimeError(f"{self.name} only runs in a live flow")
|
||||||
|
return asyncio.run_coroutine_threadsafe(work, self._loop)
|
||||||
|
|
||||||
def _say(self, **values: Any) -> None:
|
def _say(self, **values: Any) -> None:
|
||||||
"""Publish on the ports that are wired."""
|
"""Publish on the ports that are wired."""
|
||||||
wired = {spec.port for spec in self.output_ports if spec.name}
|
wired = {spec.port for spec in self.output_ports if spec.name}
|
||||||
@@ -231,18 +239,21 @@ class SttNode(_Speech):
|
|||||||
|
|
||||||
def _spawn(self, work: Coroutine[Any, Any, None]) -> None:
|
def _spawn(self, work: Coroutine[Any, Any, None]) -> None:
|
||||||
"""Run on the engine's loop, so this run can return at once."""
|
"""Run on the engine's loop, so this run can return at once."""
|
||||||
if self._loop is None:
|
task = self._call(work)
|
||||||
work.close()
|
|
||||||
raise RuntimeError("stt only hears in a live flow")
|
|
||||||
task = asyncio.run_coroutine_threadsafe(work, self._loop)
|
|
||||||
self._tasks.add(task)
|
self._tasks.add(task)
|
||||||
task.add_done_callback(self._tasks.discard)
|
task.add_done_callback(self._tasks.discard)
|
||||||
|
|
||||||
def _open(self, url: str) -> asyncio.Queue[bytes | None]:
|
def _open(self, url: str) -> asyncio.Queue[bytes | None]:
|
||||||
chunks: asyncio.Queue[bytes | None] = asyncio.Queue()
|
chunks: asyncio.Queue[bytes | None] = asyncio.Queue()
|
||||||
self._spawn(self._transcribe(url, chunks))
|
self._spawn(self._transcribe(url, chunks))
|
||||||
|
# The reply's first sentence then finds the connection open.
|
||||||
|
self._spawn(self._warm(url))
|
||||||
return chunks
|
return chunks
|
||||||
|
|
||||||
|
async def _warm(self, url: str) -> None:
|
||||||
|
with contextlib.suppress(Exception):
|
||||||
|
await client.warm(url + "/v1")
|
||||||
|
|
||||||
def _feed(self, chunks: asyncio.Queue[bytes | None], chunk: bytes | None) -> None:
|
def _feed(self, chunks: asyncio.Queue[bytes | None], chunk: bytes | None) -> None:
|
||||||
assert self._loop is not None
|
assert self._loop is not None
|
||||||
self._loop.call_soon_threadsafe(chunks.put_nowait, chunk)
|
self._loop.call_soon_threadsafe(chunks.put_nowait, chunk)
|
||||||
@@ -355,7 +366,7 @@ class TtsNode(_Speech):
|
|||||||
reference = spoken.get(key)
|
reference = spoken.get(key)
|
||||||
if reference is not None and self._artifacts.has(reference["digest"]):
|
if reference is not None and self._artifacts.has(reference["digest"]):
|
||||||
return dict(reference)
|
return dict(reference)
|
||||||
data = asyncio.run(client.speak(url + "/v1", sentence, self.cfg.voice))
|
data = self._call(client.speak(url + "/v1", sentence, self.cfg.voice)).result()
|
||||||
stored: dict[str, Any] = self._artifacts.put(
|
stored: dict[str, Any] = self._artifacts.put(
|
||||||
[data], name="speech.mp3", media_type="audio/mpeg"
|
[data], name="speech.mp3", media_type="audio/mpeg"
|
||||||
)
|
)
|
||||||
|
|||||||
@@ -52,6 +52,12 @@ def test_an_utterance_is_one_session_committed_when_listening_ends(monkeypatch):
|
|||||||
yield True, " Turn on the light."
|
yield True, " Turn on the light."
|
||||||
|
|
||||||
monkeypatch.setattr(client, "transcribe_stream", session)
|
monkeypatch.setattr(client, "transcribe_stream", session)
|
||||||
|
warmed: list[str] = []
|
||||||
|
|
||||||
|
async def warm(api_base):
|
||||||
|
warmed.append(api_base)
|
||||||
|
|
||||||
|
monkeypatch.setattr(client, "warm", warm)
|
||||||
|
|
||||||
async def scenario() -> None:
|
async def scenario() -> None:
|
||||||
node = SttNode(
|
node = SttNode(
|
||||||
@@ -94,6 +100,8 @@ def test_an_utterance_is_one_session_committed_when_listening_ends(monkeypatch):
|
|||||||
assert pipeline.state["voice.text"] == "Turn on the light."
|
assert pipeline.state["voice.text"] == "Turn on the light."
|
||||||
assert pipeline.state["voice.partial"] == "Turn on the light."
|
assert pipeline.state["voice.partial"] == "Turn on the light."
|
||||||
assert node._session is None
|
assert node._session is None
|
||||||
|
# Opened with the session, for the reply's first sentence.
|
||||||
|
assert warmed == [f"{URL}/v1"]
|
||||||
|
|
||||||
# No server, no session: the node says so instead.
|
# No server, no session: the node says so instead.
|
||||||
await hear(chunks[1], True, url="")
|
await hear(chunks[1], True, url="")
|
||||||
@@ -131,10 +139,16 @@ def test_a_sentence_is_spoken_once_and_the_rest_of_a_reply_queues(monkeypatch):
|
|||||||
Pipeline([node])
|
Pipeline([node])
|
||||||
node._artifacts = Store()
|
node._artifacts = Store()
|
||||||
|
|
||||||
node.execute({"voice.reply": "Kitchen light on. Heating off.", "voice.url": URL})
|
async def scenario() -> None:
|
||||||
# Long after both stopped playing.
|
node._loop = asyncio.get_running_loop()
|
||||||
node._until = -10.0
|
reply = "Kitchen light on. Heating off."
|
||||||
node.execute({"voice.reply": "Kitchen light on.", "voice.url": URL})
|
await asyncio.to_thread(node.execute, {"voice.reply": reply, "voice.url": URL})
|
||||||
|
# Long after both stopped playing.
|
||||||
|
node._until = -10.0
|
||||||
|
reply = "Kitchen light on."
|
||||||
|
await asyncio.to_thread(node.execute, {"voice.reply": reply, "voice.url": URL})
|
||||||
|
|
||||||
|
asyncio.run(scenario())
|
||||||
|
|
||||||
assert spoken == ["Kitchen light on.", "Heating off."]
|
assert spoken == ["Kitchen light on.", "Heating off."]
|
||||||
assert ["append" in speech for speech in published] == [False, True, False]
|
assert ["append" in speech for speech in published] == [False, True, False]
|
||||||
|
|||||||
@@ -460,7 +460,8 @@ such as one that sends whole clips.
|
|||||||
| `voice` | `af_heart` | one of Kokoro's voices, such as `bm_george` |
|
| `voice` | `af_heart` | one of Kokoro's voices, such as `bm_george` |
|
||||||
|
|
||||||
Each sentence is one call to `{url}/v1/audio/speech` and published as soon as
|
Each sentence is one call to `{url}/v1/audio/speech` and published as soon as
|
||||||
it is spoken. A sentence spoken before in the same voice is reused rather than
|
it is spoken. Calls to one server share a connection, which Speech to text opens
|
||||||
|
when an utterance starts, so a reply's first sentence does not wait for one. A sentence spoken before in the same voice is reused rather than
|
||||||
spoken again, for the last 256 sentences. A reference carries `"append": true`
|
spoken again, for the last 256 sentences. A reference carries `"append": true`
|
||||||
while the sentences before it are still playing, which queues it on a panel's
|
while the sentences before it are still playing, which queues it on a panel's
|
||||||
`speaker`. The first sentence of a reply carries none and cuts off whatever
|
`speaker`. The first sentence of a reply carries none and cuts off whatever
|
||||||
|
|||||||
Reference in New Issue
Block a user