From c2dee5e3c29eba79e591d9e9caebaef15ea4e56b Mon Sep 17 00:00:00 2001
From: hnluo <haoneng.lhn@alibaba-inc.com>
Date: 星期四, 29 六月 2023 11:09:28 +0800
Subject: [PATCH] Merge pull request #687 from alibaba-damo-academy/dev_lhn
---
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer.py | 1
/dev/null | 53 -----------------
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/demo.py | 12 ++++
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/README.md | 3
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer.sh | 105 +++++++++++++++++++++++++++++++++++
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/utils | 1
6 files changed, 120 insertions(+), 55 deletions(-)
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/README.md b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/README.md
index eff933e..9a84f9b 100644
--- a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/README.md
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/README.md
@@ -41,8 +41,7 @@
- Modify inference related parameters in `infer_after_finetune.py`
- <strong>output_dir:</strong> # result dir
- <strong>data_dir:</strong> # the dataset dir needs to include `test/wav.scp`. If `test/text` is also exists, CER will be computed
- - <strong>decoding_model_name:</strong> # set the checkpoint name for decoding, e.g., `valid.cer_ctc.ave
- .pb`
+ - <strong>decoding_model_name:</strong> # set the checkpoint name for decoding, e.g., `valid.cer_ctc.ave.pb`
- Then you can run the pipeline to finetune with:
```python
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/demo.py b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/demo.py
new file mode 100644
index 0000000..7ca7118
--- /dev/null
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/demo.py
@@ -0,0 +1,12 @@
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+
+decoding_mode="normal" #fast, normal, offline
+inference_pipeline = pipeline(
+ task=Tasks.auto_speech_recognition,
+ model='damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online',
+ param_dict={"decoding_model": decoding_mode}
+)
+
+rec_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')
+print(rec_result)
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer.py b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer.py
deleted file mode 100644
index 876d51c..0000000
--- a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer.py
+++ /dev/null
@@ -1,88 +0,0 @@
-import os
-import shutil
-from multiprocessing import Pool
-
-from modelscope.pipelines import pipeline
-from modelscope.utils.constant import Tasks
-
-from funasr.utils.compute_wer import compute_wer
-
-
-def modelscope_infer_core(output_dir, split_dir, njob, idx):
- output_dir_job = os.path.join(output_dir, "output.{}".format(idx))
- gpu_id = (int(idx) - 1) // njob
- if "CUDA_VISIBLE_DEVICES" in os.environ.keys():
- gpu_list = os.environ['CUDA_VISIBLE_DEVICES'].split(",")
- os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_list[gpu_id])
- else:
- os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id)
- inference_pipeline = pipeline(
- task=Tasks.auto_speech_recognition,
- model="damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online",
- output_dir=output_dir_job,
- batch_size=1
- )
- audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
- inference_pipeline(audio_in=audio_in, param_dict={"decoding_model": "normal"})
-
-
-def modelscope_infer(params):
- # prepare for multi-GPU decoding
- ngpu = params["ngpu"]
- njob = params["njob"]
- output_dir = params["output_dir"]
- if os.path.exists(output_dir):
- shutil.rmtree(output_dir)
- os.mkdir(output_dir)
- split_dir = os.path.join(output_dir, "split")
- os.mkdir(split_dir)
- nj = ngpu * njob
- wav_scp_file = os.path.join(params["data_dir"], "wav.scp")
- with open(wav_scp_file) as f:
- lines = f.readlines()
- num_lines = len(lines)
- num_job_lines = num_lines // nj
- start = 0
- for i in range(nj):
- end = start + num_job_lines
- file = os.path.join(split_dir, "wav.{}.scp".format(str(i + 1)))
- with open(file, "w") as f:
- if i == nj - 1:
- f.writelines(lines[start:])
- else:
- f.writelines(lines[start:end])
- start = end
-
- p = Pool(nj)
- for i in range(nj):
- p.apply_async(modelscope_infer_core,
- args=(output_dir, split_dir, njob, str(i + 1)))
- p.close()
- p.join()
-
- # combine decoding results
- best_recog_path = os.path.join(output_dir, "1best_recog")
- os.mkdir(best_recog_path)
- files = ["text", "token", "score"]
- for file in files:
- with open(os.path.join(best_recog_path, file), "w") as f:
- for i in range(nj):
- job_file = os.path.join(output_dir, "output.{}/1best_recog".format(str(i + 1)), file)
- with open(job_file) as f_job:
- lines = f_job.readlines()
- f.writelines(lines)
-
- # If text exists, compute CER
- text_in = os.path.join(params["data_dir"], "text")
- if os.path.exists(text_in):
- text_proc_file = os.path.join(best_recog_path, "text")
- compute_wer(text_in, text_proc_file, os.path.join(best_recog_path, "text.cer"))
-
-
-if __name__ == "__main__":
- params = {}
- params["data_dir"] = "./data/test"
- params["output_dir"] = "./results"
- params["ngpu"] = 1
- params["njob"] = 1
- modelscope_infer(params)
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer.py b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer.py
new file mode 120000
index 0000000..128fc31
--- /dev/null
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer.py
@@ -0,0 +1 @@
+../../TEMPLATE/infer.py
\ No newline at end of file
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer.sh b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer.sh
new file mode 100644
index 0000000..2d7a2da
--- /dev/null
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer.sh
@@ -0,0 +1,105 @@
+#!/usr/bin/env bash
+
+set -e
+set -u
+set -o pipefail
+
+stage=1
+stop_stage=2
+model="damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online"
+data_dir="./data/test"
+output_dir="./results"
+batch_size=1
+gpu_inference=false # whether to perform gpu decoding
+gpuid_list="-1" # set gpus, e.g., gpuid_list="0,1"
+njob=32 # the number of jobs for CPU decoding, if gpu_inference=false, use CPU decoding, please set njob
+checkpoint_dir=
+checkpoint_name="valid.cer_ctc.ave.pb"
+decoding_mode="normal"
+
+. utils/parse_options.sh || exit 1;
+
+if ${gpu_inference} == "true"; then
+ nj=$(echo $gpuid_list | awk -F "," '{print NF}')
+else
+ nj=$njob
+ batch_size=1
+ gpuid_list=""
+ for JOB in $(seq ${nj}); do
+ gpuid_list=$gpuid_list"-1,"
+ done
+fi
+
+mkdir -p $output_dir/split
+split_scps=""
+for JOB in $(seq ${nj}); do
+ split_scps="$split_scps $output_dir/split/wav.$JOB.scp"
+done
+perl utils/split_scp.pl ${data_dir}/wav.scp ${split_scps}
+
+if [ -n "${checkpoint_dir}" ]; then
+ python utils/prepare_checkpoint.py ${model} ${checkpoint_dir} ${checkpoint_name}
+ model=${checkpoint_dir}/${model}
+fi
+
+if [ $stage -le 1 ] && [ $stop_stage -ge 1 ];then
+ echo "Decoding ..."
+ gpuid_list_array=(${gpuid_list//,/ })
+ for JOB in $(seq ${nj}); do
+ {
+ id=$((JOB-1))
+ gpuid=${gpuid_list_array[$id]}
+ mkdir -p ${output_dir}/output.$JOB
+ python infer.py \
+ --model ${model} \
+ --audio_in ${output_dir}/split/wav.$JOB.scp \
+ --output_dir ${output_dir}/output.$JOB \
+ --batch_size ${batch_size} \
+ --gpuid ${gpuid} \
+ --decoding_mode ${decoding_mode}
+ }&
+ done
+ wait
+
+ mkdir -p ${output_dir}/1best_recog
+ for f in token score text; do
+ if [ -f "${output_dir}/output.1/1best_recog/${f}" ]; then
+ for i in $(seq "${nj}"); do
+ cat "${output_dir}/output.${i}/1best_recog/${f}"
+ done | sort -k1 >"${output_dir}/1best_recog/${f}"
+ fi
+ done
+fi
+
+if [ $stage -le 2 ] && [ $stop_stage -ge 2 ];then
+ echo "Computing WER ..."
+ cp ${output_dir}/1best_recog/text ${output_dir}/1best_recog/text.proc
+ cp ${data_dir}/text ${output_dir}/1best_recog/text.ref
+ python utils/compute_wer.py ${output_dir}/1best_recog/text.ref ${output_dir}/1best_recog/text.proc ${output_dir}/1best_recog/text.cer
+ tail -n 3 ${output_dir}/1best_recog/text.cer
+fi
+
+if [ $stage -le 3 ] && [ $stop_stage -ge 3 ];then
+ echo "SpeechIO TIOBE textnorm"
+ echo "$0 --> Normalizing REF text ..."
+ ./utils/textnorm_zh.py \
+ --has_key --to_upper \
+ ${data_dir}/text \
+ ${output_dir}/1best_recog/ref.txt
+
+ echo "$0 --> Normalizing HYP text ..."
+ ./utils/textnorm_zh.py \
+ --has_key --to_upper \
+ ${output_dir}/1best_recog/text.proc \
+ ${output_dir}/1best_recog/rec.txt
+ grep -v $'\t$' ${output_dir}/1best_recog/rec.txt > ${output_dir}/1best_recog/rec_non_empty.txt
+
+ echo "$0 --> computing WER/CER and alignment ..."
+ ./utils/error_rate_zh \
+ --tokenizer char \
+ --ref ${output_dir}/1best_recog/ref.txt \
+ --hyp ${output_dir}/1best_recog/rec_non_empty.txt \
+ ${output_dir}/1best_recog/DETAILS.txt | tee ${output_dir}/1best_recog/RESULTS.txt
+ rm -rf ${output_dir}/1best_recog/rec.txt ${output_dir}/1best_recog/rec_non_empty.txt
+fi
+
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer_after_finetune.py b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer_after_finetune.py
deleted file mode 100644
index fd124ff..0000000
--- a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer_after_finetune.py
+++ /dev/null
@@ -1,53 +0,0 @@
-import json
-import os
-import shutil
-
-from modelscope.pipelines import pipeline
-from modelscope.utils.constant import Tasks
-
-from funasr.utils.compute_wer import compute_wer
-
-
-def modelscope_infer_after_finetune(params):
- # prepare for decoding
- pretrained_model_path = os.path.join(os.environ["HOME"], ".cache/modelscope/hub", params["modelscope_model_name"])
- for file_name in params["required_files"]:
- if file_name == "configuration.json":
- with open(os.path.join(pretrained_model_path, file_name)) as f:
- config_dict = json.load(f)
- config_dict["model"]["am_model_name"] = params["decoding_model_name"]
- with open(os.path.join(params["output_dir"], "configuration.json"), "w") as f:
- json.dump(config_dict, f, indent=4, separators=(',', ': '))
- else:
- shutil.copy(os.path.join(pretrained_model_path, file_name),
- os.path.join(params["output_dir"], file_name))
- decoding_path = os.path.join(params["output_dir"], "decode_results")
- if os.path.exists(decoding_path):
- shutil.rmtree(decoding_path)
- os.mkdir(decoding_path)
-
- # decoding
- inference_pipeline = pipeline(
- task=Tasks.auto_speech_recognition,
- model=params["output_dir"],
- output_dir=decoding_path,
- batch_size=1
- )
- audio_in = os.path.join(params["data_dir"], "wav.scp")
- inference_pipeline(audio_in=audio_in, param_dict={"decoding_model": "normal"})
-
- # computer CER if GT text is set
- text_in = os.path.join(params["data_dir"], "text")
- if os.path.exists(text_in):
- text_proc_file = os.path.join(decoding_path, "1best_recog/text")
- compute_wer(text_in, text_proc_file, os.path.join(decoding_path, "text.cer"))
-
-
-if __name__ == '__main__':
- params = {}
- params["modelscope_model_name"] = "damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online"
- params["required_files"] = ["am.mvn", "decoding.yaml", "configuration.json"]
- params["output_dir"] = "./checkpoint"
- params["data_dir"] = "./data/test"
- params["decoding_model_name"] = "20epoch.pb"
- modelscope_infer_after_finetune(params)
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/utils b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/utils
new file mode 120000
index 0000000..2ac163f
--- /dev/null
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/utils
@@ -0,0 +1 @@
+../../../../egs/aishell/transformer/utils
\ No newline at end of file
--
Gitblit v1.9.1