[文档、验收与归档]：完成真实运行说明和OpenSpec归档，包含README、最终门禁和主规范更新
This commit is contained in:
mkbk
@@ -13,7 +13,7 @@ class AppConfig:
|
||||
channels: int = 1
|
||||
llm_base_url: str = "https://token-plan-cn.xiaomimimo.com/v1"
|
||||
llm_api_key: str | None = None
|
||||
llm_model: str = "gpt-5.4-mini"
|
||||
llm_model: str = "mimo-v2.5"
|
||||
llm_api_style: str = "chat_completions"
|
||||
llm_stream: bool = True
|
||||
audio_input_device: str | None = None
|
||||
@@ -23,7 +23,7 @@ class AppConfig:
|
||||
speech_provider: str = "cloud"
|
||||
asr_model: str = "mimo-v2.5-asr"
|
||||
tts_model: str = "mimo-v2.5-tts"
|
||||
tts_voice: str = "alloy"
|
||||
tts_voice: str = "mimo_default"
|
||||
speech_models_dir: Path = Path("models")
|
||||
context_max_messages: int = 12
|
||||
context_max_chars: int = 12000
|
||||
@@ -42,7 +42,7 @@ class AppConfig:
|
||||
channels=int(get("CHANNELS", "1") or "1"),
|
||||
llm_base_url=(get("LLM_BASE_URL", "https://token-plan-cn.xiaomimimo.com/v1") or "").rstrip("/"),
|
||||
llm_api_key=get("LLM_API_KEY"),
|
||||
llm_model=get("LLM_MODEL", "gpt-5.4-mini") or "gpt-5.4-mini",
|
||||
llm_model=get("LLM_MODEL", "mimo-v2.5") or "mimo-v2.5",
|
||||
llm_api_style=get("LLM_API_STYLE", "chat_completions") or "chat_completions",
|
||||
llm_stream=(get("LLM_STREAM", "1") or "1").lower() not in {"0", "false", "no"},
|
||||
audio_input_device=get("AUDIO_INPUT_DEVICE"),
|
||||
@@ -52,7 +52,7 @@ class AppConfig:
|
||||
speech_provider=(get("SPEECH_PROVIDER", "cloud") or "cloud").lower(),
|
||||
asr_model=get("ASR_MODEL", "mimo-v2.5-asr") or "mimo-v2.5-asr",
|
||||
tts_model=get("TTS_MODEL", "mimo-v2.5-tts") or "mimo-v2.5-tts",
|
||||
tts_voice=get("TTS_VOICE", "alloy") or "alloy",
|
||||
tts_voice=get("TTS_VOICE", "mimo_default") or "mimo_default",
|
||||
speech_models_dir=Path(get("SPEECH_MODELS_DIR", "models") or "models"),
|
||||
context_max_messages=int(get("CONTEXT_MAX_MESSAGES", "12") or "12"),
|
||||
context_max_chars=int(get("CONTEXT_MAX_CHARS", "12000") or "12000"),
|
||||
|
||||
+23
-36
@@ -1,12 +1,12 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import io
|
||||
import base64
|
||||
import json
|
||||
import re
|
||||
import socket
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
import uuid
|
||||
import wave
|
||||
from collections.abc import Callable
|
||||
from pathlib import Path
|
||||
@@ -84,19 +84,28 @@ class CloudAsrSttProvider:
|
||||
"newapi-asr",
|
||||
"stt",
|
||||
)
|
||||
wav_bytes = _segment_to_wav_bytes(segment)
|
||||
boundary = "owner-voice-pet-" + uuid.uuid4().hex
|
||||
body = _multipart_form_data(
|
||||
boundary,
|
||||
fields={"model": self.config.asr_model, "response_format": "json"},
|
||||
files={"file": ("utterance.wav", "audio/wav", wav_bytes)},
|
||||
)
|
||||
audio_data = base64.b64encode(_segment_to_wav_bytes(segment)).decode("ascii")
|
||||
payload = {
|
||||
"model": self.config.asr_model,
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": [
|
||||
{
|
||||
"type": "input_audio",
|
||||
"input_audio": {"data": f"data:audio/wav;base64,{audio_data}"},
|
||||
}
|
||||
],
|
||||
}
|
||||
],
|
||||
"asr_options": {"language": "auto"},
|
||||
}
|
||||
request = urllib.request.Request(
|
||||
self.config.api_url("/v1/audio/transcriptions"),
|
||||
data=body,
|
||||
self.config.api_url("/v1/chat/completions"),
|
||||
data=json.dumps(payload).encode("utf-8"),
|
||||
headers={
|
||||
"Authorization": f"Bearer {self.config.llm_api_key}",
|
||||
"Content-Type": f"multipart/form-data; boundary={boundary}",
|
||||
"Content-Type": "application/json",
|
||||
},
|
||||
method="POST",
|
||||
)
|
||||
@@ -119,7 +128,9 @@ class CloudAsrSttProvider:
|
||||
"newapi-asr",
|
||||
"stt",
|
||||
) from exc
|
||||
text = str(payload.get("text") or "").strip()
|
||||
choices = payload.get("choices") or []
|
||||
message = (choices[0].get("message") if choices else {}) or {}
|
||||
text = str(message.get("content") or payload.get("text") or "").strip()
|
||||
if not is_valid_transcript_text(text):
|
||||
raise ProviderError(
|
||||
ErrorCode.STT_EMPTY_TRANSCRIPT,
|
||||
@@ -261,27 +272,3 @@ def _segment_to_wav_bytes(segment: AudioSegment) -> bytes:
|
||||
wav.setframerate(segment.sample_rate)
|
||||
wav.writeframes(segment.pcm)
|
||||
return buffer.getvalue()
|
||||
|
||||
|
||||
def _multipart_form_data(
|
||||
boundary: str,
|
||||
*,
|
||||
fields: dict[str, str],
|
||||
files: dict[str, tuple[str, str, bytes]],
|
||||
) -> bytes:
|
||||
body = bytearray()
|
||||
for name, value in fields.items():
|
||||
body.extend(f"--{boundary}\r\n".encode())
|
||||
body.extend(f'Content-Disposition: form-data; name="{name}"\r\n\r\n'.encode())
|
||||
body.extend(value.encode("utf-8"))
|
||||
body.extend(b"\r\n")
|
||||
for name, (filename, content_type, data) in files.items():
|
||||
body.extend(f"--{boundary}\r\n".encode())
|
||||
body.extend(
|
||||
f'Content-Disposition: form-data; name="{name}"; filename="{filename}"\r\n'.encode()
|
||||
)
|
||||
body.extend(f"Content-Type: {content_type}\r\n\r\n".encode())
|
||||
body.extend(data)
|
||||
body.extend(b"\r\n")
|
||||
body.extend(f"--{boundary}--\r\n".encode())
|
||||
return bytes(body)
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import math
|
||||
import base64
|
||||
import json
|
||||
import socket
|
||||
import struct
|
||||
@@ -166,12 +167,12 @@ class CloudTtsProvider:
|
||||
)
|
||||
payload = {
|
||||
"model": self.config.tts_model,
|
||||
"input": clean,
|
||||
"voice": self.config.tts_voice,
|
||||
"response_format": "mp3",
|
||||
"messages": [{"role": "assistant", "content": clean}],
|
||||
"audio": {"format": "wav", "voice": self.config.tts_voice},
|
||||
"stream": False,
|
||||
}
|
||||
request = urllib.request.Request(
|
||||
self.config.api_url("/v1/audio/speech"),
|
||||
self.config.api_url("/v1/chat/completions"),
|
||||
data=json.dumps(payload).encode("utf-8"),
|
||||
headers={
|
||||
"Authorization": f"Bearer {self.config.llm_api_key}",
|
||||
@@ -181,7 +182,7 @@ class CloudTtsProvider:
|
||||
)
|
||||
try:
|
||||
with self.urlopen(request, timeout=self.timeout_s) as response:
|
||||
data = response.read()
|
||||
payload = json.loads(response.read().decode("utf-8"))
|
||||
except urllib.error.HTTPError as exc:
|
||||
raise ProviderError(
|
||||
ErrorCode.TTS_SYNTHESIS_FAILED,
|
||||
@@ -190,7 +191,7 @@ class CloudTtsProvider:
|
||||
"newapi-tts",
|
||||
"tts",
|
||||
) from exc
|
||||
except (urllib.error.URLError, TimeoutError, socket.timeout) as exc:
|
||||
except (urllib.error.URLError, TimeoutError, socket.timeout, json.JSONDecodeError) as exc:
|
||||
raise ProviderError(
|
||||
ErrorCode.TTS_SYNTHESIS_FAILED,
|
||||
f"cloud TTS request failed: {exc}",
|
||||
@@ -198,7 +199,11 @@ class CloudTtsProvider:
|
||||
"newapi-tts",
|
||||
"tts",
|
||||
) from exc
|
||||
if not data:
|
||||
choices = payload.get("choices") or []
|
||||
message = (choices[0].get("message") if choices else {}) or {}
|
||||
audio = message.get("audio") or {}
|
||||
encoded = audio.get("data")
|
||||
if not encoded:
|
||||
raise ProviderError(
|
||||
ErrorCode.TTS_EMPTY_AUDIO,
|
||||
"cloud TTS returned empty audio",
|
||||
@@ -206,4 +211,14 @@ class CloudTtsProvider:
|
||||
"newapi-tts",
|
||||
"tts",
|
||||
)
|
||||
return AudioSegment(data, 16000, 1, 0, max(120, len(clean) * 45), {"text": clean, "format": "mp3"})
|
||||
try:
|
||||
data = base64.b64decode(encoded)
|
||||
except (TypeError, ValueError) as exc:
|
||||
raise ProviderError(
|
||||
ErrorCode.TTS_SYNTHESIS_FAILED,
|
||||
f"cloud TTS returned invalid base64 audio: {exc}",
|
||||
True,
|
||||
"newapi-tts",
|
||||
"tts",
|
||||
) from exc
|
||||
return AudioSegment(data, 24000, 1, 0, max(120, len(clean) * 45), {"text": clean, "format": "wav"})
|
||||
|
||||
Reference in New Issue
Block a user