first commit for takway.ai

2024-05-18 15:50:56 +08:00
commit d7a6de771c
@@ -0,0 +1,28 @@
+#!/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="/Users/zhifu/Downloads/modelscope_models/SenseVoiceModelscope",
+    # vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",
+    # vad_kwargs={"max_single_segment_time": 30000},
+)
+
+
+input_wav = (
+    "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav"
+)
+
+DecodingOptions = {
+    "task": ("ASR", "AED", "SER"),
+    "language": "auto",
+    "fp16": True,
+    "gain_event": True,
+    "beam_size": 5,
+}
+
+res = model.generate(input=input_wav, batch_size_s=0, DecodingOptions=DecodingOptions)
+print(res)
@@ -0,0 +1,28 @@
+#!/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="/Users/zhifu/Downloads/modelscope_models/SenseVoiceModelscopeFSMN",
+    vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",
+    vad_kwargs={"max_single_segment_time": 30000},
+)
+
+
+input_wav = (
+    "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav"
+)
+
+DecodingOptions = {
+    "task": ("ASR", "AED", "SER"),
+    "language": "auto",
+    "fp16": True,
+    "gain_event": True,
+    "beam_size": 5,
+}
+
+res = model.generate(input=input_wav, batch_size_s=0, DecodingOptions=DecodingOptions, beam_size=5)
+print(res)
@@ -0,0 +1,69 @@
+# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
+#  MIT License  (https://opensource.org/licenses/MIT)
+
+
+# which gpu to train or finetune
+export CUDA_VISIBLE_DEVICES="0"
+gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
+
+# model_name from model_hub, or model_dir in local path
+
+## option 1, download model automatically
+model_name_or_model_dir="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
+model_name_or_model_dir="/Users/zhifu/Downloads/modelscope_models/SenseVoiceModelscope"
+## option 2, download model by git
+#local_path_root=${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}"
+
+#torchrun \
+#--nnodes 1 \
+#--node_rank 0 \
+#--nproc_per_node ${gpu_num} \
+python \
+../../../funasr/bin/train.py \
++model="${model_name_or_model_dir}" \
++train_data_set_list="${train_data}" \
++valid_data_set_list="${val_data}" \
++dataset_conf.batch_size=500 \
++dataset_conf.batch_type="token" \
++dataset_conf.num_workers=0 \
++train_conf.max_epoch=50 \
++train_conf.log_interval=1 \
++train_conf.resume=false \
++train_conf.validate_interval=2000 \
++train_conf.save_checkpoint_interval=2000 \
++train_conf.keep_nbest_models=20 \
++train_conf.avg_nbest_model=10 \
++optim_conf.lr=0.0002 \
++debug=true \
++device="cpu" \
++output_dir="${output_dir}" #&> ${log_file}