Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Python asraudiochineseemotion-recognitionfunasrmcp-servermultilingual-asropenai-compatible-apiparaformerpunctuationpytorchreal-time-asrspeaker-diarizationspeech-recognitionspeech-to-textstreaming-asrtranscriptionvllmvoice-activity-detectionwhisper-alternative
add test
语帆ea71c0f891ab
diff --git a/.gitignore b/.gitignoreindex 6bdfd5d06..23864c3e0 100644--- a/.gitignore+++ b/.gitignore@@ -24,3 +24,4 @@ samplesoutputs*emotion2vec*GPT-SoVITS*+examples/*/*/outputsdiff --git a/examples/industrial_data_pretraining/contextual_paraformer/demo.py b/examples/industrial_data_pretraining/contextual_paraformer/demo.pyold mode 100644new mode 100755diff --git a/examples/industrial_data_pretraining/contextual_paraformer/demo2.py b/examples/industrial_data_pretraining/contextual_paraformer/demo2.pynew file mode 100644index 000000000..30bb76fbc--- /dev/null+++ b/examples/industrial_data_pretraining/contextual_paraformer/demo2.py@@ -0,0 +1,9 @@+python -m funasr.bin.inference \+--config-path="/mnt/workspace/FunASR/examples/aishell/paraformer/exp/baseline_paraformer_conformer_12e_6d_2048_256_zh_char_exp3" \+--config-name="config.yaml" \+++init_param="/mnt/workspace/FunASR/examples/aishell/paraformer/exp/baseline_paraformer_conformer_12e_6d_2048_256_zh_char_exp3/model.pt.ep38" \+++tokenizer_conf.token_list="/mnt/nfs/zhifu.gzf/data/AISHELL-1-feats/DATA/data/zh_token_list/char/tokens.txt" \+++frontend_conf.cmvn_file="/mnt/nfs/zhifu.gzf/data/AISHELL-1-feats/DATA/data/train/am.mvn" \+++input="/mnt/nfs/zhifu.gzf/data/AISHELL-1/data_aishell/wav/train/S0002/BAC009S0002W0122.wav" \+++output_dir="./outputs/debug" \+++device="cuda:0" \diff --git a/examples/industrial_data_pretraining/contextual_paraformer/infer.sh b/examples/industrial_data_pretraining/contextual_paraformer/infer.shold mode 100644new mode 100755index 8fc66f34f..1bd4f7f5b--- a/examples/industrial_data_pretraining/contextual_paraformer/infer.sh+++ b/examples/industrial_data_pretraining/contextual_paraformer/infer.sh@@ -2,7 +2,7 @@model="damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404"model_revision="v2.0.4"-python funasr/bin/inference.py \+python ../../../funasr/bin/inference.py \+model=${model} \+model_revision=${model_revision} \+input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav" \diff --git a/examples/industrial_data_pretraining/contextual_paraformer/path.sh b/examples/industrial_data_pretraining/contextual_paraformer/path.shnew file mode 100755index 000000000..1a6d67e08--- /dev/null+++ b/examples/industrial_data_pretraining/contextual_paraformer/path.sh@@ -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