From f57b68121a526baea43b2e93f4540d8a2995f633 Mon Sep 17 00:00:00 2001 From: 游雁 <zhifu.gzf@alibaba-inc.com> Date: 星期一, 29 四月 2024 15:15:24 +0800 Subject: [PATCH] batch --- examples/industrial_data_pretraining/seaco_paraformer/demo.py | 34 +++++++++++++++++++--------------- 1 files changed, 19 insertions(+), 15 deletions(-) diff --git a/examples/industrial_data_pretraining/seaco_paraformer/demo.py b/examples/industrial_data_pretraining/seaco_paraformer/demo.py index e9e226d..a88e880 100644 --- a/examples/industrial_data_pretraining/seaco_paraformer/demo.py +++ b/examples/industrial_data_pretraining/seaco_paraformer/demo.py @@ -5,26 +5,30 @@ from funasr import AutoModel -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", - ) +model = AutoModel( + model="iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch", + # vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch", + # punc_model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch", + # spk_model="iic/speech_campplus_sv_zh-cn_16k-common", +) # 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', - # sentence_timestamp=True, # return sentence level information when spk_model is not given - ) +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) @@ -33,8 +37,8 @@ # example3 import soundfile -import os + 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