6a62a43d61
Generation Page (complete rebuild): - Full production-parity exam generation wizard with 4 IELTS modules - Reading: AI passage gen, 5 exercise types (MCQ, Fill, Write, T/F, Match) - Listening: 4 section types, AI context gen, TTS audio gen (ElevenLabs) - Writing: Task 1/2, AI instruction gen, word limits, marks - Speaking: 3 parts, AI script gen, avatar video gen (7 avatars) - Per-module config: timer, CEFR difficulty, access, approval, rubrics - Exam submission workflow (draft/published) Exam Structures: - New encoach.exam.structure model + CRUD controller - ExamStructuresPage wired to real API AI Module (encoach_ai): - OpenAI service, ElevenLabs TTS, AWS Polly, ELAI avatars - AI settings model with Odoo config parameters - 7 generation endpoints (passage, exercises, instructions, scripts, context) Vector Module (encoach_vector): - pgvector integration for RAG-based content search - Embedding service with sentence-transformers Exam Session Fixes: - Fixed ExamSession.tsx field mapping (question_type→type, exam_title→title) - Fixed submit payload to include attempt_id and answers - Fixed normalizeType to handle null/undefined Tested: 12/12 API tests passed, browser-verified with real OpenAI calls Made-with: Cursor
111 lines
3.6 KiB
Python
111 lines
3.6 KiB
Python
"""OpenAI Whisper speech-to-text service."""
|
|
|
|
import logging
|
|
import tempfile
|
|
import time
|
|
|
|
_logger = logging.getLogger(__name__)
|
|
|
|
try:
|
|
import whisper as _whisper_mod
|
|
except ImportError:
|
|
_whisper_mod = None
|
|
|
|
try:
|
|
import openai as _openai_mod
|
|
except ImportError:
|
|
_openai_mod = None
|
|
|
|
|
|
class WhisperService:
|
|
"""Speech-to-text via local Whisper model or OpenAI Whisper API."""
|
|
|
|
def __init__(self, env):
|
|
self.env = env
|
|
self._get_param = env["ir.config_parameter"].sudo().get_param
|
|
self._local_model = None
|
|
api_key = self._get_param("encoach_ai.openai_api_key", "")
|
|
if not api_key:
|
|
import os
|
|
api_key = os.environ.get("OPENAI_API_KEY", "")
|
|
self._api_key = api_key
|
|
|
|
def _get_local_model(self):
|
|
if not _whisper_mod:
|
|
return None
|
|
if self._local_model is None:
|
|
self._local_model = _whisper_mod.load_model("base")
|
|
return self._local_model
|
|
|
|
def _log(self, action, latency, status="success", error=None):
|
|
try:
|
|
self.env["encoach.ai.log"].sudo().create({
|
|
"service": "whisper",
|
|
"action": action,
|
|
"latency_ms": latency,
|
|
"status": status,
|
|
"error_message": error,
|
|
})
|
|
except Exception:
|
|
pass
|
|
|
|
def transcribe(self, audio_data, *, language="en", use_api=False):
|
|
"""Transcribe audio bytes to text.
|
|
|
|
Args:
|
|
audio_data: Raw audio bytes (wav, mp3, webm, etc.)
|
|
language: Language code
|
|
use_api: If True, use OpenAI Whisper API instead of local model
|
|
Returns:
|
|
dict with 'text', 'language', 'segments' keys
|
|
"""
|
|
t0 = time.time()
|
|
|
|
if use_api and self._api_key and _openai_mod:
|
|
return self._transcribe_api(audio_data, language, t0)
|
|
|
|
model = self._get_local_model()
|
|
if model:
|
|
return self._transcribe_local(model, audio_data, language, t0)
|
|
|
|
if self._api_key and _openai_mod:
|
|
return self._transcribe_api(audio_data, language, t0)
|
|
|
|
raise RuntimeError("Whisper not available — install whisper package or set OpenAI API key")
|
|
|
|
def _transcribe_local(self, model, audio_data, language, t0):
|
|
with tempfile.NamedTemporaryFile(suffix=".webm", delete=True) as tmp:
|
|
tmp.write(audio_data)
|
|
tmp.flush()
|
|
result = model.transcribe(tmp.name, language=language)
|
|
latency = int((time.time() - t0) * 1000)
|
|
self._log("transcribe_local", latency)
|
|
return {
|
|
"text": result["text"].strip(),
|
|
"language": result.get("language", language),
|
|
"segments": [
|
|
{"start": s["start"], "end": s["end"], "text": s["text"]}
|
|
for s in result.get("segments", [])
|
|
],
|
|
}
|
|
|
|
def _transcribe_api(self, audio_data, language, t0):
|
|
client = _openai_mod.OpenAI(api_key=self._api_key)
|
|
with tempfile.NamedTemporaryFile(suffix=".webm", delete=True) as tmp:
|
|
tmp.write(audio_data)
|
|
tmp.flush()
|
|
tmp.seek(0)
|
|
result = client.audio.transcriptions.create(
|
|
model="whisper-1",
|
|
file=tmp,
|
|
language=language,
|
|
response_format="verbose_json",
|
|
)
|
|
latency = int((time.time() - t0) * 1000)
|
|
self._log("transcribe_api", latency)
|
|
return {
|
|
"text": result.text.strip() if hasattr(result, "text") else str(result),
|
|
"language": language,
|
|
"segments": getattr(result, "segments", []),
|
|
}
|