From d3d2fe73c08ee51d3a44d7ffb7b31eff32b60404 Mon Sep 17 00:00:00 2001 From: 游雁 <zhifu.gzf@alibaba-inc.com> Date: 星期一, 18 三月 2024 20:46:23 +0800 Subject: [PATCH] wav fronend --- examples/industrial_data_pretraining/whisper/demo_from_openai.py | 7 +++++-- 1 files changed, 5 insertions(+), 2 deletions(-) diff --git a/examples/industrial_data_pretraining/whisper/demo_from_openai.py b/examples/industrial_data_pretraining/whisper/demo_from_openai.py index 0b88a95..5cac06b 100644 --- a/examples/industrial_data_pretraining/whisper/demo_from_openai.py +++ b/examples/industrial_data_pretraining/whisper/demo_from_openai.py @@ -3,15 +3,18 @@ # Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved. # MIT License (https://opensource.org/licenses/MIT) +# To install requirements: pip3 install -U openai-whisper + from funasr import AutoModel # model = AutoModel(model="Whisper-small", hub="openai") # model = AutoModel(model="Whisper-medium", hub="openai") -model = AutoModel(model="Whisper-large-v2", hub="openai") -# model = AutoModel(model="Whisper-large-v3", hub="openai") +# model = AutoModel(model="Whisper-large-v2", hub="openai") +model = AutoModel(model="Whisper-large-v3", hub="openai", vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",) res = model.generate( language=None, task="transcribe", + batch_size_s=0, input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav") print(res) -- Gitblit v1.9.1