8f05a7c188
- Update ASR, face, OCR, pose processors - Add release pre-flight check script - Add synonym generation, chunk processing scripts - Add face recognition, stamp search utilities
86 lines
2.4 KiB
Python
Executable File
86 lines
2.4 KiB
Python
Executable File
#!/opt/homebrew/bin/python3.11
|
|
"""
|
|
SpeechBrain 測試腳本
|
|
測試 ASR 和說話人分離功能
|
|
"""
|
|
|
|
import sys
|
|
import json
|
|
import time
|
|
from pathlib import Path
|
|
|
|
def test_asr(video_path):
|
|
"""測試 SpeechBrain ASR"""
|
|
print(f"[SpeechBrain] Testing ASR on: {video_path}")
|
|
|
|
try:
|
|
from speechbrain.inference.ASR import EncoderDecoderASR
|
|
|
|
# 載入模型
|
|
print("[SpeechBrain] Loading ASR model...")
|
|
asr_model = EncoderDecoderASR.from_hparams(
|
|
source="speechbrain/asr-wav2vec2-commonvoice-en",
|
|
savedir="pretrained_models/asr-wav2vec2-commonvoice-en"
|
|
)
|
|
|
|
# 轉錄
|
|
print("[SpeechBrain] Transcribing...")
|
|
start_time = time.time()
|
|
|
|
# SpeechBrain 需要 WAV 檔案
|
|
# 這裡我們先測試基本功能
|
|
print("[SpeechBrain] Note: SpeechBrain requires WAV format")
|
|
print("[SpeechBrain] Testing basic model loading... OK")
|
|
|
|
elapsed = time.time() - start_time
|
|
print(f"[SpeechBrain] Model loaded in {elapsed:.2f}s")
|
|
|
|
return True
|
|
|
|
except Exception as e:
|
|
print(f"[SpeechBrain] Error: {e}")
|
|
import traceback
|
|
traceback.print_exc()
|
|
return False
|
|
|
|
|
|
def test_speaker_diarization(audio_path):
|
|
"""測試說話人分離"""
|
|
print(f"[SpeechBrain] Testing speaker diarization on: {audio_path}")
|
|
|
|
try:
|
|
from speechbrain.inference.speaker import SpeakerRecognition
|
|
|
|
print("[SpeechBrain] Loading speaker recognition model...")
|
|
verification = SpeakerRecognition.from_hparams(
|
|
source="speechbrain/spkrec-ecapa-voxceleb",
|
|
savedir="pretrained_models/spkrec-ecapa-voxceleb"
|
|
)
|
|
|
|
print("[SpeechBrain] Model loaded successfully")
|
|
return True
|
|
|
|
except Exception as e:
|
|
print(f"[SpeechBrain] Speaker diarization error: {e}")
|
|
return False
|
|
|
|
|
|
if __name__ == "__main__":
|
|
video_path = sys.argv[1] if len(sys.argv) > 1 else "/tmp/test.wav"
|
|
|
|
print("=== SpeechBrain 測試 ===")
|
|
print("")
|
|
|
|
# 測試 ASR
|
|
asr_ok = test_asr(video_path)
|
|
print("")
|
|
|
|
# 測試說話人分離
|
|
spk_ok = test_speaker_diarization(video_path)
|
|
print("")
|
|
|
|
# 總結
|
|
print("=== 測試結果 ===")
|
|
print(f"ASR: {'✅ 成功' if asr_ok else '❌ 失敗'}")
|
|
print(f"Speaker Diarization: {'✅ 成功' if spk_ok else '❌ 失敗'}")
|