From 8a100b731efba8c18f7e7b6cb1cb04ded94248b3 Mon Sep 17 00:00:00 2001
From: aky15 <ankeyu.aky@11.17.44.249>
Date: 星期二, 21 三月 2023 14:52:15 +0800
Subject: [PATCH] add aishell-1 rnnt egs
---
funasr/bin/asr_inference_launch.py | 88 +++++++++++++++++++++++++++++++++++++++++++
1 files changed, 87 insertions(+), 1 deletions(-)
diff --git a/funasr/bin/asr_inference_launch.py b/funasr/bin/asr_inference_launch.py
index 67a85d2..b9be3e2 100644
--- a/funasr/bin/asr_inference_launch.py
+++ b/funasr/bin/asr_inference_launch.py
@@ -131,6 +131,11 @@
help="Pretrained model tag. If specify this option, *_train_config and "
"*_file will be overwritten",
)
+ group.add_argument(
+ "--beam_search_config",
+ default={},
+ help="The keyword arguments for transducer beam search.",
+ )
group = parser.add_argument_group("Beam-search related")
group.add_argument(
@@ -168,6 +173,41 @@
group.add_argument("--lm_weight", type=float, default=1.0, help="RNNLM weight")
group.add_argument("--ngram_weight", type=float, default=0.9, help="ngram weight")
group.add_argument("--streaming", type=str2bool, default=False)
+ group.add_argument("--simu_streaming", type=str2bool, default=False)
+ group.add_argument("--chunk_size", type=int, default=16)
+ group.add_argument("--left_context", type=int, default=16)
+ group.add_argument("--right_context", type=int, default=0)
+ group.add_argument(
+ "--display_partial_hypotheses",
+ type=bool,
+ default=False,
+ help="Whether to display partial hypotheses during chunk-by-chunk inference.",
+ )
+
+ group = parser.add_argument_group("Dynamic quantization related")
+ group.add_argument(
+ "--quantize_asr_model",
+ type=bool,
+ default=False,
+ help="Apply dynamic quantization to ASR model.",
+ )
+ group.add_argument(
+ "--quantize_modules",
+ nargs="*",
+ default=None,
+ help="""Module names to apply dynamic quantization on.
+ The module names are provided as a list, where each name is separated
+ by a comma (e.g.: --quantize-config=[Linear,LSTM,GRU]).
+ Each specified name should be an attribute of 'torch.nn', e.g.:
+ torch.nn.Linear, torch.nn.LSTM, torch.nn.GRU, ...""",
+ )
+ group.add_argument(
+ "--quantize_dtype",
+ type=str,
+ default="qint8",
+ choices=["float16", "qint8"],
+ help="Dtype for dynamic quantization.",
+ )
group = parser.add_argument_group("Text converter related")
group.add_argument(
@@ -210,15 +250,61 @@
elif mode == "uniasr":
from funasr.bin.asr_inference_uniasr import inference_modelscope
return inference_modelscope(**kwargs)
+ elif mode == "uniasr_vad":
+ from funasr.bin.asr_inference_uniasr_vad import inference_modelscope
+ return inference_modelscope(**kwargs)
elif mode == "paraformer":
from funasr.bin.asr_inference_paraformer import inference_modelscope
return inference_modelscope(**kwargs)
+ elif mode == "paraformer_vad":
+ from funasr.bin.asr_inference_paraformer_vad import inference_modelscope
+ return inference_modelscope(**kwargs)
+ elif mode == "paraformer_punc":
+ logging.info("Unknown decoding mode: {}".format(mode))
+ return None
elif mode == "paraformer_vad_punc":
from funasr.bin.asr_inference_paraformer_vad_punc import inference_modelscope
return inference_modelscope(**kwargs)
elif mode == "vad":
from funasr.bin.vad_inference import inference_modelscope
return inference_modelscope(**kwargs)
+ elif mode == "mfcca":
+ from funasr.bin.asr_inference_mfcca import inference_modelscope
+ return inference_modelscope(**kwargs)
+ elif mode == "rnnt":
+ from funasr.bin.asr_inference_rnnt import inference_modelscope
+ return inference_modelscope(**kwargs)
+ else:
+ logging.info("Unknown decoding mode: {}".format(mode))
+ return None
+
+def inference_launch_funasr(**kwargs):
+ if 'mode' in kwargs:
+ mode = kwargs['mode']
+ else:
+ logging.info("Unknown decoding mode.")
+ return None
+ if mode == "asr":
+ from funasr.bin.asr_inference import inference
+ return inference(**kwargs)
+ elif mode == "uniasr":
+ from funasr.bin.asr_inference_uniasr import inference
+ return inference(**kwargs)
+ elif mode == "paraformer":
+ from funasr.bin.asr_inference_paraformer import inference
+ return inference(**kwargs)
+ elif mode == "paraformer_vad_punc":
+ from funasr.bin.asr_inference_paraformer_vad_punc import inference
+ return inference(**kwargs)
+ elif mode == "vad":
+ from funasr.bin.vad_inference import inference
+ return inference(**kwargs)
+ elif mode == "mfcca":
+ from funasr.bin.asr_inference_mfcca import inference_modelscope
+ return inference_modelscope(**kwargs)
+ elif mode == "rnnt":
+ from funasr.bin.asr_inference_rnnt import inference
+ return inference(**kwargs)
else:
logging.info("Unknown decoding mode: {}".format(mode))
return None
@@ -251,7 +337,7 @@
os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
os.environ["CUDA_VISIBLE_DEVICES"] = gpuid
- inference_launch(**kwargs)
+ inference_launch_funasr(**kwargs)
if __name__ == "__main__":
--
Gitblit v1.9.1