From 4137f5cf26e7c4b40853959cd2574edfde03aa60 Mon Sep 17 00:00:00 2001
From: 志浩 <neo.dzh@alibaba-inc.com>
Date: 星期五, 07 四月 2023 21:03:34 +0800
Subject: [PATCH] Merge branch 'main' of github.com:alibaba-damo-academy/FunASR into dev_dzh
---
egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer.py | 95 ++++++++---------------------------------------
1 files changed, 16 insertions(+), 79 deletions(-)
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer.py b/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer.py
index f08b31f..7cc71e7 100644
--- a/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer.py
+++ b/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer.py
@@ -1,88 +1,25 @@
import os
import shutil
-from multiprocessing import Pool
-
+import argparse
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_pipline = pipeline(
+def modelscope_infer(args):
+ os.environ['CUDA_VISIBLE_DEVICES'] = str(args.gpuid)
+ inference_pipeline = pipeline(
task=Tasks.auto_speech_recognition,
- model="damo/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1",
- output_dir=output_dir_job,
- batch_size=64
+ model=args.model,
+ output_dir=args.output_dir,
+ batch_size=args.batch_size,
)
- audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
- inference_pipline(audio_in=audio_in)
-
-
-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, "token")
- compute_wer(text_in, text_proc_file, os.path.join(best_recog_path, "text.cer"))
-
+ inference_pipeline(audio_in=args.audio_in)
if __name__ == "__main__":
- params = {}
- params["data_dir"] = "./data/test"
- params["output_dir"] = "./results"
- params["ngpu"] = 1
- params["njob"] = 1
- modelscope_infer(params)
+ parser = argparse.ArgumentParser()
+ parser.add_argument('--model', type=str, default="damo/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1")
+ parser.add_argument('--audio_in', type=str, default="./data/test/wav.scp")
+ parser.add_argument('--output_dir', type=str, default="./results/")
+ parser.add_argument('--batch_size', type=int, default=64)
+ parser.add_argument('--gpuid', type=str, default="0")
+ args = parser.parse_args()
+ modelscope_infer(args)
\ No newline at end of file
--
Gitblit v1.9.1