From 3a4281f4959534b1bf5d01acf0085f4f8e6f2ec8 Mon Sep 17 00:00:00 2001
From: wuhongsheng <664116298@qq.com>
Date: 星期五, 05 七月 2024 00:55:32 +0800
Subject: [PATCH] 优化speakid和语句匹配逻辑，部分解决speakid不从0递增问题 (#1870)
---
examples/industrial_data_pretraining/emotion2vec/demo.py | 20 +++++++++++++++++---
1 files changed, 17 insertions(+), 3 deletions(-)
diff --git a/examples/industrial_data_pretraining/emotion2vec/demo.py b/examples/industrial_data_pretraining/emotion2vec/demo.py
index a41641e..71f69bb 100644
--- a/examples/industrial_data_pretraining/emotion2vec/demo.py
+++ b/examples/industrial_data_pretraining/emotion2vec/demo.py
@@ -5,8 +5,22 @@
from funasr import AutoModel
-model = AutoModel(model="damo/emotion2vec_base", model_revision="v2.0.1")
+# model="iic/emotion2vec_base"
+# model="iic/emotion2vec_base_finetuned"
+# model="iic/emotion2vec_plus_seed"
+# model="iic/emotion2vec_plus_base"
+model = "iic/emotion2vec_plus_large"
+
+model = AutoModel(
+ model=model,
+ # vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",
+ # vad_model_revision="master",
+ # vad_kwargs={"max_single_segment_time": 2000},
+)
wav_file = f"{model.model_path}/example/test.wav"
-res = model.generate(wav_file, output_dir="./outputs", granularity="utterance")
-print(res)
\ No newline at end of file
+
+res = model.generate(
+ wav_file, output_dir="./outputs", granularity="utterance", extract_embedding=False
+)
+print(res)
--
Gitblit v1.9.1