From a11c08faa4500b02e72e8b039d6acf67b8585a34 Mon Sep 17 00:00:00 2001
From: Your Name <your-email@example.com>
Date: Fri, 20 Feb 2026 23:52:28 -0800
Subject: [PATCH] Fix #2787: skip validate_frame_rate for raw PCM bytes in
 load_bytes

`validate_frame_rate` calls `pydub.AudioSegment.from_file` which takes
~200 ms.  When the caller passes raw PCM bytes (no container header) the
call always fails and the exception is silently swallowed, wasting 200 ms
on every invocation.

Add a lightweight `_is_audio_container` helper that inspects the first
few magic bytes of the input.  `load_bytes` now only calls
`validate_frame_rate` when the payload is a recognised container format
(WAV / MP3 / OGG / FLAC / MP4).  Raw PCM buffers skip the validation
entirely, eliminating the latency hit.

Also remove a stray `import pdb` debug statement.
---
 funasr/utils/load_utils.py | 40 +++++++++++++++++++++++++++++++++-----
 1 file changed, 35 insertions(+), 5 deletions(-)

diff --git a/funasr/utils/load_utils.py b/funasr/utils/load_utils.py
index d208f7dc0..ba6ef22c3 100644
--- a/funasr/utils/load_utils.py
+++ b/funasr/utils/load_utils.py
@@ -15,7 +15,6 @@
     from funasr.download.file import download_from_url
 except:
     print("urllib is not installed, if you infer from url, please install it first.")
-import pdb
 import subprocess
 from subprocess import CalledProcessError, run
 
@@ -144,11 +143,42 @@ def load_audio_text_image_video(
     return data_or_path_or_list
 
 
+def _is_audio_container(data: bytes) -> bool:
+    """Return True if *data* starts with a recognised container-format magic header.
+
+    Raw PCM byte streams have no header, so they will return False and the
+    expensive pydub/ffmpeg validation round-trip can be skipped entirely.
+    """
+    if len(data) < 4:
+        return False
+    # WAV  – RIFF....WAVE
+    if data[:4] == b"RIFF":
+        return True
+    # MP3  – ID3 tag or sync word (0xFF 0xEx)
+    if data[:3] == b"ID3" or (data[0] == 0xFF and (data[1] & 0xE0) == 0xE0):
+        return True
+    # OGG
+    if data[:4] == b"OggS":
+        return True
+    # FLAC
+    if data[:4] == b"fLaC":
+        return True
+    # MP4 / M4A / AAC  – 'ftyp' box at offset 4
+    if len(data) >= 8 and data[4:8] == b"ftyp":
+        return True
+    return False
+
+
 def load_bytes(input):
-    try:
-        input = validate_frame_rate(input)
-    except:
-        pass
+    # Only run the (expensive) frame-rate validation when the payload is an
+    # actual audio container (WAV, MP3, OGG, …).  Raw PCM buffers have no
+    # recognisable header and would cause pydub to spend ~200 ms before
+    # raising an exception that is then silently swallowed anyway.
+    if _is_audio_container(input):
+        try:
+            input = validate_frame_rate(input)
+        except:
+            pass
     middle_data = np.frombuffer(input, dtype=np.int16)
     middle_data = np.asarray(middle_data)
     if middle_data.dtype.kind not in "iu":