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 +1,14 @@
+#!/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_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404")
+
+res = model.generate(
+    input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav",
+    hotword="达摩院 魔搭",
+)
+print(res)
@@ -0,0 +1,11 @@
+
+model="iic/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404"
+
+
+python ../../../funasr/bin/inference.py \
+model=${model} \
+input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav" \
+output_dir="./outputs/debug" \
+device="cpu" \
+"hotword='达摩院 魔搭'"
+
@@ -0,0 +1,9 @@
+python -m funasr.bin.inference \
+--config-path="/nfs/yufan.yf/workspace/model_download/modelscope/hub/damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404" \
+--config-name="config.yaml" \
++init_param="/nfs/yufan.yf/workspace/model_download/modelscope/hub/damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/model.pb" \
++tokenizer_conf.token_list="/nfs/yufan.yf/workspace/model_download/modelscope/hub/damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/tokens.txt" \
++frontend_conf.cmvn_file="/nfs/yufan.yf/workspace/model_download/modelscope/hub/damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/am.mvn" \
++input="/nfs/yufan.yf/workspace/model_download/modelscope/hub/damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/asr_example_zh.wav" \
++output_dir="./outputs/debug2" \
++device="" \
@@ -0,0 +1,85 @@
+# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
+#  MIT License  (https://opensource.org/licenses/MIT)
+
+workspace=`pwd`
+
+# method1, finetune from model hub
+
+# which gpu to train or finetune
+export CUDA_VISIBLE_DEVICES="0,1"
+gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
+
+# model_name from model_hub, or model_dir in local path
+
+## option 1, download model automatically
+model_name_or_model_dir="iic/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404"
+
+
+## option 2, download model by git
+#local_path_root=${workspace}/modelscope_models
+#mkdir -p ${local_path_root}/${model_name_or_model_dir}
+#git clone https://www.modelscope.cn/${model_name_or_model_dir}.git ${local_path_root}/${model_name_or_model_dir}
+#model_name_or_model_dir=${local_path_root}/${model_name_or_model_dir}
+
+
+# data dir, which contains: train.json, val.json
+data_dir="../../../data/list"
+
+train_data="${data_dir}/train.jsonl"
+val_data="${data_dir}/val.jsonl"
+
+# generate train.jsonl and val.jsonl from wav.scp and text.txt
+scp2jsonl \
++scp_file_list='["../../../data/list/train_wav.scp", "../../../data/list/train_text.txt"]' \
++data_type_list='["source", "target"]' \
++jsonl_file_out="${train_data}"
+
+scp2jsonl \
++scp_file_list='["../../../data/list/val_wav.scp", "../../../data/list/val_text.txt"]' \
++data_type_list='["source", "target"]' \
++jsonl_file_out="${val_data}"
+
+
+# exp output dir
+output_dir="./outputs"
+log_file="${output_dir}/log.txt"
+
+
+mkdir -p ${output_dir}
+echo "log_file: ${log_file}"
+
+deepspeed_config=${workspace}/../../ds_stage1.json
+
+DISTRIBUTED_ARGS="
+    --nnodes ${WORLD_SIZE:-1} \
+    --nproc_per_node $gpu_num \
+    --node_rank ${RANK:-0} \
+    --master_addr ${MASTER_ADDR:-127.0.0.1} \
+    --master_port ${MASTER_PORT:-26669}
+"
+
+echo $DISTRIBUTED_ARGS
+
+torchrun $DISTRIBUTED_ARGS \
+../../../funasr/bin/train_ds.py \
++model="${model_name_or_model_dir}" \
++train_data_set_list="${train_data}" \
++valid_data_set_list="${val_data}" \
++dataset="AudioDatasetHotword" \
++dataset_conf.index_ds="IndexDSJsonl" \
++dataset_conf.data_split_num=1 \
++dataset_conf.batch_sampler="BatchSampler" \
++dataset_conf.batch_size=6000  \
++dataset_conf.sort_size=1024 \
++dataset_conf.batch_type="token" \
++dataset_conf.num_workers=4 \
++train_conf.max_epoch=50 \
++train_conf.log_interval=1 \
++train_conf.resume=true \
++train_conf.validate_interval=2000 \
++train_conf.save_checkpoint_interval=2000 \
++train_conf.keep_nbest_models=20 \
++train_conf.use_deepspeed=false \
++train_conf.deepspeed_config=${deepspeed_config} \
++optim_conf.lr=0.0002 \
++output_dir="${output_dir}" &> ${log_file}
@@ -0,0 +1,6 @@
+export FUNASR_DIR=$PWD/../../../
+
+# NOTE(kan-bayashi): Use UTF-8 in Python to avoid UnicodeDecodeError when LC_ALL=C
+export PYTHONIOENCODING=UTF-8
+export PATH=$FUNASR_DIR/funasr/bin:$PATH
+export PYTHONPATH=$FUNASR_DIR/funasr/bin:$FUNASR_DIR/funasr:$FUNASR_DIR:$PYTHONPATH