From eb1574b813e230b156fc09eaaf03227b1b0b4134 Mon Sep 17 00:00:00 2001
From: weilikai <jasper@talkus.fun>
Date: 星期六, 20 九月 2025 22:41:05 +0800
Subject: [PATCH] fix: support loading .pcm (16k 1c 16bit) audio files in load_utils.py (#2667) (#2668)
---
funasr/utils/load_utils.py | 9 +++++++++
1 files changed, 9 insertions(+), 0 deletions(-)
diff --git a/funasr/utils/load_utils.py b/funasr/utils/load_utils.py
index c38f1d9..d208f7d 100644
--- a/funasr/utils/load_utils.py
+++ b/funasr/utils/load_utils.py
@@ -241,10 +241,19 @@
# This launches a subprocess to decode audio while down-mixing
# and resampling as necessary. Requires the ffmpeg CLI in PATH.
# fmt: off
+ pcm_params = []
+ if file.lower().endswith('.pcm'):
+ pcm_params = [
+ "-f", "s16le",
+ "-ar", str(sr),
+ "-ac", "1"
+ ]
+
cmd = [
"ffmpeg",
"-nostdin",
"-threads", "0",
+ *pcm_params, # PCM files need input format specified before -i since PCM is raw data without headers
"-i", file,
"-f", "s16le",
"-ac", "1",
--
Gitblit v1.9.1