New PR for Faster Whisper: Batching Support, Speed Boosts, and Qualit…

…y Enhancements (SYSTRAN#856)

Batching Support, Speed Boosts, and Quality Enhancements

---------

Co-authored-by: Hargun Mujral <83234565+hargunmujral@users.noreply.github.com>
Co-authored-by: MahmoudAshraf97 <hassouna97.ma@gmail.com>

tests/test_transcribe.py

@@ -145,6 +145,13 @@ def test_stereo_diarization(data_dir):
     assert transcription == "The horizon seems extremely distant."
 
 
+def test_multisegment_lang_id(physcisworks_path):
+    model = WhisperModel("tiny")
+    language_info = model.detect_language_multi_segment(physcisworks_path)
+    assert language_info["language_code"] == "en"
+    assert language_info["language_confidence"] > 0.8
+
+
 def test_suppressed_tokens_minus_1():
     model = WhisperModel("tiny.en")