From 38de2af5bf9976d2f14f087d9a0d31991daf6783 Mon Sep 17 00:00:00 2001
From: Zhihao Du <neo.dzh@alibaba-inc.com>
Date: 星期四, 16 三月 2023 19:41:34 +0800
Subject: [PATCH] Merge branch 'main' into dev_dzh
---
egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.py | 31 ++++++++++++++++++++++---------
1 files changed, 22 insertions(+), 9 deletions(-)
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.py b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.py
index f9f6114..795a1e7 100644
--- a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.py
+++ b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.py
@@ -8,9 +8,14 @@
from funasr.utils.compute_wer import compute_wer
-def modelscope_infer_core(output_dir, split_dir, njob, idx):
+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))
- gpu_id = (int(idx) - 1) // njob
+ 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])
@@ -18,9 +23,10 @@
os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id)
inference_pipline = pipeline(
task=Tasks.auto_speech_recognition,
- model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
+ model=model,
output_dir=output_dir_job,
- batch_size=64
+ batch_size=batch_size,
+ ngpu=use_gpu,
)
audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
inference_pipline(audio_in=audio_in)
@@ -30,13 +36,18 @@
# 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)
- nj = ngpu * njob
+ 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()
@@ -56,7 +67,7 @@
p = Pool(nj)
for i in range(nj):
p.apply_async(modelscope_infer_core,
- args=(output_dir, split_dir, njob, str(i + 1)))
+ args=(output_dir, split_dir, njob, str(i + 1), batch_size, ngpu, model))
p.close()
p.join()
@@ -81,8 +92,10 @@
if __name__ == "__main__":
params = {}
+ params["model"] = "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
params["data_dir"] = "./data/test"
params["output_dir"] = "./results"
- params["ngpu"] = 1
- params["njob"] = 1
- modelscope_infer(params)
+ 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)
\ No newline at end of file
--
Gitblit v1.9.1