From 3ac03e448b7673604eb86f619b27521fca55f34d Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 21 三月 2024 01:36:39 +0800
Subject: [PATCH] train & finetune llm-asr (#1519)
---
examples/industrial_data_pretraining/paraformer_streaming/demo.py | 7 ++++---
1 files changed, 4 insertions(+), 3 deletions(-)
diff --git a/examples/industrial_data_pretraining/paraformer_streaming/demo.py b/examples/industrial_data_pretraining/paraformer_streaming/demo.py
index 9885c0b..601a531 100644
--- a/examples/industrial_data_pretraining/paraformer_streaming/demo.py
+++ b/examples/industrial_data_pretraining/paraformer_streaming/demo.py
@@ -8,20 +8,21 @@
chunk_size = [5, 10, 5] #[0, 10, 5] 600ms, [0, 8, 4] 480ms
encoder_chunk_look_back = 0 #number of chunks to lookback for encoder self-attention
decoder_chunk_look_back = 0 #number of encoder chunks to lookback for decoder cross-attention
-
+wav_file="/Users/zhifu/Downloads/NCYzUhAtZNI_0015.wav"
model = AutoModel(model="iic/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online", model_revision="v2.0.4")
-res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav",
+res = model.generate(input=wav_file,
chunk_size=chunk_size,
encoder_chunk_look_back=encoder_chunk_look_back,
decoder_chunk_look_back=decoder_chunk_look_back,
)
print(res)
+# exit()
import soundfile
import os
-wav_file = os.path.join(model.model_path, "example/asr_example.wav")
+# wav_file = os.path.join(model.model_path, "example/asr_example.wav")
speech, sample_rate = soundfile.read(wav_file)
chunk_stride = chunk_size[1] * 960 # 600ms銆�480ms
--
Gitblit v1.9.1