feat: ASRX hybrid pipeline, identity history, worker fixes, checkpoint system

scripts/asrx_self/whisper_local.py

@@ -0,0 +1,35 @@
+"""
+Whisper Local - uses faster-whisper for per-segment transcription
+"""
+
+import numpy as np
+
+
+def load_model(size="small"):
+    from faster_whisper import WhisperModel
+    return WhisperModel(size, device="cpu", compute_type="int8")
+
+
+def transcribe_segment(wav, sample_rate, start_sec, end_sec, model):
+    start_sample = int(start_sec * sample_rate)
+    end_sample = int(end_sec * sample_rate)
+    if start_sample >= len(wav):
+        return {"text": "", "language": "", "lang_prob": 0.0, "segments": []}
+    segment_wav = wav[start_sample:min(end_sample, len(wav))]
+
+    segments_generator, info = model.transcribe(segment_wav, language=None)
+
+    text = ""
+    lang_prob = info.language_probability if info else 0.0
+    language = info.language if info else ""
+
+    segs = list(segments_generator)
+    for seg in segs:
+        text += seg.text + " "
+
+    return {
+        "text": text.strip(),
+        "language": language,
+        "lang_prob": lang_prob,
+        "segments": segs,
+    }