From 9ba0dbd98bf69c830dfcfde8f109a400cb65e4e5 Mon Sep 17 00:00:00 2001
From: 雾聪 <wucong.lyb@alibaba-inc.com>
Date: 星期五, 29 三月 2024 17:24:59 +0800
Subject: [PATCH] fix func Forward
---
examples/industrial_data_pretraining/seaco_paraformer/demo.py | 15 ++++++++++-----
1 files changed, 10 insertions(+), 5 deletions(-)
diff --git a/examples/industrial_data_pretraining/seaco_paraformer/demo.py b/examples/industrial_data_pretraining/seaco_paraformer/demo.py
index 85d989e..551dd8b 100644
--- a/examples/industrial_data_pretraining/seaco_paraformer/demo.py
+++ b/examples/industrial_data_pretraining/seaco_paraformer/demo.py
@@ -7,10 +7,10 @@
model = AutoModel(model="iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
model_revision="v2.0.4",
- vad_model="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch",
- vad_model_revision="v2.0.4",
- punc_model="damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch",
- punc_model_revision="v2.0.4",
+ # vad_model="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch",
+ # vad_model_revision="v2.0.4",
+ # punc_model="damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch",
+ # punc_model_revision="v2.0.4",
# spk_model="damo/speech_campplus_sv_zh-cn_16k-common",
# spk_model_revision="v2.0.2",
)
@@ -19,10 +19,15 @@
# example1
res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav",
hotword='杈炬懇闄� 榄旀惌',
+ # return_raw_text=True, # return raw text recognition results splited by space of equal length with timestamp
+ # preset_spk_num=2, # preset speaker num for speaker cluster model
# sentence_timestamp=True, # return sentence level information when spk_model is not given
)
print(res)
+
+'''
+# tensor or numpy as input
# example2
import torchaudio
import os
@@ -38,4 +43,4 @@
wav_file = os.path.join(model.model_path, "example/asr_example.wav")
speech, sample_rate = soundfile.read(wav_file)
res = model.generate(input=[speech], batch_size_s=300, is_final=True)
-
+'''
--
Gitblit v1.9.1