From 61c24582f9483e7b4330b8a92e634110a98424e1 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 05 七月 2023 17:28:09 +0800
Subject: [PATCH] funasr sdk
---
funasr/runtime/python/websocket/funasr_wss_client.py | 13 +++++++++++--
funasr/runtime/python/websocket/README.md | 8 ++++++++
funasr/runtime/docs/SDK_advanced_guide_offline_zh.md | 2 +-
3 files changed, 20 insertions(+), 3 deletions(-)
diff --git a/funasr/runtime/docs/SDK_advanced_guide_offline_zh.md b/funasr/runtime/docs/SDK_advanced_guide_offline_zh.md
index b32df1f..0242d5d 100644
--- a/funasr/runtime/docs/SDK_advanced_guide_offline_zh.md
+++ b/funasr/runtime/docs/SDK_advanced_guide_offline_zh.md
@@ -36,7 +36,7 @@
```
鎴戜滑浠ython璇█瀹㈡埛绔负渚嬶紝杩涜璇存槑锛屾敮鎸佸绉嶉煶棰戞牸寮忚緭鍏ワ紙.wav, .pcm, .mp3绛夛級锛屼篃鏀寔瑙嗛杈撳叆(.mp4绛�)锛屼互鍙婂鏂囦欢鍒楄〃wav.scp杈撳叆锛屽叾浠栫増鏈鎴风璇峰弬鑰冩枃妗ｏ紙[鐐瑰嚮姝ゅ](#瀹㈡埛绔敤娉曡瑙�)锛夛紝瀹氬埗鏈嶅姟閮ㄧ讲璇峰弬鑰僛濡備綍瀹氬埗鏈嶅姟閮ㄧ讲](#濡備綍瀹氬埗鏈嶅姟閮ㄧ讲)
```shell
-python3 wss_client_asr.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "../audio/asr_example.wav" --output_dir "./results"
+python3 wss_client_asr.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "../audio/asr_example.wav"
```
------------------
diff --git a/funasr/runtime/python/websocket/README.md b/funasr/runtime/python/websocket/README.md
index bbad639..686ad86 100644
--- a/funasr/runtime/python/websocket/README.md
+++ b/funasr/runtime/python/websocket/README.md
@@ -47,6 +47,14 @@
cd funasr/runtime/python/websocket
pip install -r requirements_client.txt
```
+If you want infer from videos, you should install `ffmpeg`
+```shell
+apt-get install -y ffmpeg #ubuntu
+# yum install -y ffmpeg # centos
+# brew install ffmpeg # mac
+# winget install ffmpeg # wins
+pip3 install websockets ffmpeg-python
+```
### Start client
#### API-reference
diff --git a/funasr/runtime/python/websocket/funasr_wss_client.py b/funasr/runtime/python/websocket/funasr_wss_client.py
index a3f5405..d91d9d1 100644
--- a/funasr/runtime/python/websocket/funasr_wss_client.py
+++ b/funasr/runtime/python/websocket/funasr_wss_client.py
@@ -138,8 +138,17 @@
frames = wav_file.readframes(wav_file.getnframes())
audio_bytes = bytes(frames)
else:
- raise NotImplementedError(
- f'Not supported audio type')
+ import ffmpeg
+ try:
+ # This launches a subprocess to decode audio while down-mixing and resampling as necessary.
+ # Requires the ffmpeg CLI and `ffmpeg-python` package to be installed.
+ audio_bytes, _ = (
+ ffmpeg.input(wav_path, threads=0)
+ .output("-", format="s16le", acodec="pcm_s16le", ac=1, ar=16000)
+ .run(cmd=["ffmpeg", "-nostdin"], capture_stdout=True, capture_stderr=True)
+ )
+ except ffmpeg.Error as e:
+ raise RuntimeError(f"Failed to load audio: {e.stderr.decode()}") from e
# stride = int(args.chunk_size/1000*16000*2)
stride = int(60 * args.chunk_size[1] / args.chunk_interval / 1000 * 16000 * 2)
--
Gitblit v1.9.1