|
|
@@ -1,101 +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, batch_size, ngpu, model):
|
|
|
- output_dir_job = os.path.join(output_dir, "output.{}".format(idx))
|
|
|
- if ngpu > 0:
|
|
|
- use_gpu = 1
|
|
|
- gpu_id = int(idx) - 1
|
|
|
- else:
|
|
|
- use_gpu = 0
|
|
|
- gpu_id = -1
|
|
|
- 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=model,
|
|
|
- output_dir=output_dir_job,
|
|
|
- batch_size=batch_size,
|
|
|
- ngpu=use_gpu,
|
|
|
+ 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"]
|
|
|
- batch_size = params["batch_size"]
|
|
|
- output_dir = params["output_dir"]
|
|
|
- model = params["model"]
|
|
|
- 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)
|
|
|
- if ngpu > 0:
|
|
|
- nj = ngpu
|
|
|
- elif ngpu == 0:
|
|
|
- nj = 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), batch_size, ngpu, model))
|
|
|
- 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["model"] = "damo/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1"
|
|
|
- params["data_dir"] = "./data/test"
|
|
|
- params["output_dir"] = "./results"
|
|
|
- params["ngpu"] = 1 # if ngpu > 0, will use gpu decoding
|
|
|
- params["njob"] = 1 # if ngpu = 0, will use cpu decoding
|
|
|
- params["batch_size"] = 64
|
|
|
- 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")
|
|
|
+ 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)
|
北念