From 0cf5dfec2c8313fc2ed2aab8d10bf3dc4b9c283f Mon Sep 17 00:00:00 2001
From: 雾聪 <wucong.lyb@alibaba-inc.com>
Date: 星期四, 14 三月 2024 14:41:49 +0800
Subject: [PATCH] update cmakelist
---
examples/industrial_data_pretraining/seaco_paraformer/demo.py | 48 +++++++++++++++++++++++++++++++++++++-----------
1 files changed, 37 insertions(+), 11 deletions(-)
diff --git a/examples/industrial_data_pretraining/seaco_paraformer/demo.py b/examples/industrial_data_pretraining/seaco_paraformer/demo.py
index 5342fa0..551dd8b 100644
--- a/examples/industrial_data_pretraining/seaco_paraformer/demo.py
+++ b/examples/industrial_data_pretraining/seaco_paraformer/demo.py
@@ -5,16 +5,42 @@
from funasr import AutoModel
-model = AutoModel(model="damo/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
- model_revision="v2.0.2",
- vad_model="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch",
- vad_model_revision="v2.0.2",
- punc_model="damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch",
- punc_model_revision="v2.0.2",
- spk_model="damo/speech_campplus_sv_zh-cn_16k-common",
- spk_model="v2.0.2",
+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",
+ # spk_model="damo/speech_campplus_sv_zh-cn_16k-common",
+ # spk_model_revision="v2.0.2",
)
-res = model(input=f"{model.model_path}/example/asr_example.wav",
- hotword='杈炬懇闄� 榄旀惌')
-print(res)
\ No newline at end of file
+
+# 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
+wav_file = os.path.join(model.model_path, "example/asr_example.wav")
+input_tensor, sample_rate = torchaudio.load(wav_file)
+input_tensor = input_tensor.mean(0)
+res = model.generate(input=[input_tensor], batch_size_s=300, is_final=True)
+
+
+# example3
+import soundfile
+
+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