From 1011e667870e06f62d57c2c6cdea54a834ac5438 Mon Sep 17 00:00:00 2001
From: 仁迷 <haoneng.lhn@alibaba-inc.com>
Date: 星期四, 16 二月 2023 11:32:47 +0800
Subject: [PATCH] update uniasr infer recipe
---
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer.py | 2 +-
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/infer_after_finetune.py | 2 +-
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline/infer_after_finetune.py | 2 +-
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/infer.py | 2 +-
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/README.md | 2 +-
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/infer_after_finetune.py | 2 +-
egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline/infer.py | 2 +-
7 files changed, 7 insertions(+), 7 deletions(-)
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/README.md b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/README.md
index dfd509d..dd947d3 100644
--- a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/README.md
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/README.md
@@ -1,6 +1,6 @@
# ModelScope Model
-## How to finetune and infer using a pretrained Paraformer-large Model
+## How to finetune and infer using a pretrained UniASR Model
### Finetune
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/infer.py b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/infer.py
index 06b172f..d28395b 100644
--- a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/infer.py
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/infer.py
@@ -23,7 +23,7 @@
batch_size=1
)
audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
- inference_pipline(audio_in=audio_in)
+ inference_pipline(audio_in=audio_in, param_dict={"decoding_model": "normal"})
def modelscope_infer(params):
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/infer_after_finetune.py b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/infer_after_finetune.py
index 96f202a..030c2e2 100644
--- a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/infer_after_finetune.py
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-minnan-16k-common-vocab3825/infer_after_finetune.py
@@ -34,7 +34,7 @@
batch_size=1
)
audio_in = os.path.join(params["data_dir"], "wav.scp")
- inference_pipeline(audio_in=audio_in)
+ 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")
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline/infer.py b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline/infer.py
index e855032..ad0cc7a 100644
--- a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline/infer.py
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline/infer.py
@@ -23,7 +23,7 @@
batch_size=1
)
audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
- inference_pipline(audio_in=audio_in)
+ inference_pipline(audio_in=audio_in, param_dict={"decoding_model": "normal"})
def modelscope_infer(params):
diff --git a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline/infer_after_finetune.py b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline/infer_after_finetune.py
index 6664c3d..9d8700c 100644
--- a/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline/infer_after_finetune.py
+++ b/egs_modelscope/asr/uniasr/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-offline/infer_after_finetune.py
@@ -34,7 +34,7 @@
batch_size=1
)
audio_in = os.path.join(params["data_dir"], "wav.scp")
- inference_pipeline(audio_in=audio_in)
+ 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")
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
index 8fd7513..5c62362 100644
--- 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
@@ -23,7 +23,7 @@
batch_size=1
)
audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
- inference_pipline(audio_in=audio_in)
+ inference_pipline(audio_in=audio_in, param_dict={"decoding_model": "normal"})
def modelscope_infer(params):
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
index b4dde60..4860cf7 100644
--- 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
@@ -34,7 +34,7 @@
batch_size=1
)
audio_in = os.path.join(params["data_dir"], "wav.scp")
- inference_pipeline(audio_in=audio_in)
+ 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")
--
Gitblit v1.9.1