first commit for takway.ai

examples/industrial_data_pretraining/whisper/demo.py

@@ -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)
+
+# To install requirements: pip3 install -U openai-whisper
+
+from funasr import AutoModel
+
+model = AutoModel(
+    model="iic/Whisper-large-v3",
+    vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",
+    vad_kwargs={"max_single_segment_time": 30000},
+)
+
+DecodingOptions = {
+    "task": "transcribe",
+    "language": None,
+    "beam_size": None,
+    "fp16": True,
+    "without_timestamps": False,
+    "prompt": None,
+}
+res = model.generate(
+    DecodingOptions=DecodingOptions,
+    batch_size_s=0,
+    input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav",
+)
+
+print(res)

examples/industrial_data_pretraining/whisper/demo_from_openai.py

@@ -0,0 +1,34 @@
+#!/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)
+
+# To install requirements: pip3 install -U openai-whisper
+
+from funasr import AutoModel
+
+# model = AutoModel(model="Whisper-small", hub="openai")
+# model = AutoModel(model="Whisper-medium", hub="openai")
+# model = AutoModel(model="Whisper-large-v2", hub="openai")
+model = AutoModel(
+    model="Whisper-large-v3",
+    vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",
+    vad_kwargs={"max_single_segment_time": 30000},
+    hub="openai",
+)
+
+DecodingOptions = {
+    "task": "transcribe",
+    "language": None,
+    "beam_size": None,
+    "fp16": True,
+    "without_timestamps": False,
+    "prompt": None,
+}
+res = model.generate(
+    DecodingOptions=DecodingOptions,
+    batch_size_s=0,
+    input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav",
+)
+
+print(res)

examples/industrial_data_pretraining/whisper/infer.sh

@@ -0,0 +1,22 @@
+# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
+#  MIT License  (https://opensource.org/licenses/MIT)
+
+# To install requirements: pip3 install -U openai-whisper
+
+# method1, inference from model hub
+
+# for more input type, please ref to readme.md
+input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav"
+
+output_dir="./outputs/debug"
+
+model="iic/speech_whisper-large_asr_multilingual"
+
+
+device="cuda:0" # "cuda:0" for gpu0, "cuda:1" for gpu1, "cpu"
+
+python -m funasr.bin.inference \
+++model=${model} \
+++input="${input}" \
+++output_dir="${output_dir}" \
+++device="${device}" \

examples/industrial_data_pretraining/whisper/infer_from_local.sh

@@ -0,0 +1,42 @@
+# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
+#  MIT License  (https://opensource.org/licenses/MIT)
+
+# To install requirements: pip3 install -U openai-whisper
+
+# method2, inference from local model
+
+# for more input type, please ref to readme.md
+input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav"
+
+output_dir="./outputs/debug"
+
+workspace=`pwd`
+
+# download model
+local_path_root=${workspace}/modelscope_models
+mkdir -p ${local_path_root}
+#Whisper-large-v2
+#local_path=${local_path_root}/speech_whisper-large_asr_multilingual
+#git clone https://www.modelscope.cn/iic/speech_whisper-large_asr_multilingual.git ${local_path}
+#init_param="${local_path}/large-v2.pt"
+#Whisper-large-v3
+local_path=${local_path_root}/Whisper-large-v3
+git clone https://www.modelscope.cn/iic/Whisper-large-v3.git ${local_path}
+init_param="${local_path}/large-v3.pt"
+
+device="cuda:0" # "cuda:0" for gpu0, "cuda:1" for gpu1, "cpu"
+
+config="config.yaml"
+
+
+python -m funasr.bin.inference \
+--config-path "${local_path}" \
+--config-name "${config}" \
+++init_param="${init_param}" \
+++input="${input}" \
+++output_dir="${output_dir}" \
+++device="${device}" \
+
+
+
+

examples/industrial_data_pretraining/whisper/infer_from_openai.sh

@@ -0,0 +1,26 @@
+# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
+#  MIT License  (https://opensource.org/licenses/MIT)
+
+# To install requirements: pip3 install -U openai-whisper
+
+# method1, inference from model hub
+
+# for more input type, please ref to readme.md
+input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav"
+
+output_dir="./outputs/debug"
+
+#model="Whisper-small"
+#model="Whisper-medium"
+model="Whisper-large-v2"
+#model="Whisper-large-v3"
+hub="openai"
+
+device="cuda:0" # "cuda:0" for gpu0, "cuda:1" for gpu1, "cpu"
+
+python -m funasr.bin.inference \
+++model=${model} \
+++hub=${hub} \
+++input="${input}" \
+++output_dir="${output_dir}" \
+++device="${device}" \