Initial commit: FunASR Speech Recognition Toolkit

Add complete FunASR codebase including models, runtime, and documentation.
2026-07-09 22:38:58 +08:00
commit 6116b1f3c6
3683 changed files with 990984 additions and 0 deletions
@@ -0,0 +1,30 @@
+#!/usr/bin/env python3
+# -*- encoding: utf-8 -*-
+# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
+#  MIT License  (https://opensource.org/licenses/MIT)
+
+from funasr import AutoModel
+
+
+model = AutoModel(
+    model="iic/speech_UniASR-large_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-offline",
+)
+
+
+res = model.generate(
+    input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav"
+)
+print(res)
+
+
+""" can not use currently
+from funasr import AutoFrontend
+
+frontend = AutoFrontend(model="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch")
+
+fbanks = frontend(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav", batch_size=2)
+
+for batch_idx, fbank_dict in enumerate(fbanks):
+    res = model.generate(**fbank_dict)
+    print(res)
+"""
@@ -0,0 +1,10 @@
+
+model="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
+
+
+python funasr/bin/inference.py \
+model=${model} \
+input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav" \
+output_dir="./outputs/debug" \
+device="cpu" \
+