Initial commit: FunASR Speech Recognition Toolkit

Add complete FunASR codebase including models, runtime, and documentation.

examples/industrial_data_pretraining/ct_transformer/demo.py

@@ -0,0 +1,23 @@
+#!/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/punc_ct-transformer_zh-cn-common-vocab272727-pytorch")
+
+res = model.generate(
+    input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_text/punc_example.txt"
+)
+print(res)
+
+
+from funasr import AutoModel
+
+model = AutoModel(model="iic/punc_ct-transformer_cn-en-common-vocab471067-large")
+
+res = model.generate(
+    input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_text/punc_example.txt"
+)
+print(res)

examples/industrial_data_pretraining/ct_transformer/demo.sh

@@ -0,0 +1,12 @@
+
+#model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch"
+#
+
+model="iic/punc_ct-transformer_cn-en-common-vocab471067-large"
+
+
+python funasr/bin/inference.py \
++model=${model} \
++input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_text/punc_example.txt" \
++output_dir="./outputs/debug" \
++device="cpu"

examples/industrial_data_pretraining/ct_transformer/export.py

@@ -0,0 +1,26 @@
+#!/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)
+
+# method1, inference from model hub
+
+from funasr import AutoModel
+
+model = AutoModel(
+    model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch",
+)
+
+res = model.export(type="onnx", quantize=False)
+print(res)
+
+
+# method2, inference from local path
+from funasr import AutoModel
+
+model = AutoModel(
+    model="/Users/zhifu/.cache/modelscope/hub/iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch"
+)
+
+res = model.export(type="onnx", quantize=False)
+print(res)

examples/industrial_data_pretraining/ct_transformer/export.sh

@@ -0,0 +1,26 @@
+# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
+#  MIT License  (https://opensource.org/licenses/MIT)
+
+# method1, inference from model hub
+export HYDRA_FULL_ERROR=1
+
+
+model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch"
+
+
+python -m funasr.bin.export \
+++model=${model} \
+++model_revision=${model_revision} \
+++type="onnx" \
+++quantize=false \
+++device="cpu"
+
+
+# method2, inference from local path
+model="/Users/zhifu/.cache/modelscope/hub/iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch"
+
+python -m funasr.bin.export \
+++model=${model} \
+++type="onnx" \
+++quantize=false \
+++device="cpu"