From 2d078a26feae1f8b230e51ffbb9e521c85607c0d Mon Sep 17 00:00:00 2001
From: shixian.shi <shixian.shi@alibaba-inc.com>
Date: 星期四, 25 一月 2024 10:23:19 +0800
Subject: [PATCH] update umap import

---
 README_zh.md |   39 +++++++++++++++++++++++----------------
 1 files changed, 23 insertions(+), 16 deletions(-)

diff --git a/README_zh.md b/README_zh.md
index 861e61c..552a5a0 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -87,12 +87,13 @@
 from funasr import AutoModel
 # paraformer-zh is a multi-functional asr model
 # use vad, punc, spk or not as you need
-model = AutoModel(model="paraformer-zh", model_revision="v2.0.2", \
-                  vad_model="fsmn-vad", vad_model_revision="v2.0.2", \
-                  punc_model="ct-punc-c", punc_model_revision="v2.0.2", \
-                  spk_model="cam++", spk_model_revision="v2.0.2")
-res = model(input=f"{model.model_path}/example/asr_example.wav", 
-            batch_size=64, 
+model = AutoModel(model="paraformer-zh", model_revision="v2.0.4",
+                  vad_model="fsmn-vad", vad_model_revision="v2.0.4",
+                  punc_model="ct-punc-c", punc_model_revision="v2.0.4",
+                  # spk_model="cam++", spk_model_revision="v2.0.2",
+                  )
+res = model.generate(input=f"{model.model_path}/example/asr_example.wav", 
+            batch_size_s=300, 
             hotword='榄旀惌')
 print(res)
 ```
@@ -107,7 +108,7 @@
 encoder_chunk_look_back = 4 #number of chunks to lookback for encoder self-attention
 decoder_chunk_look_back = 1 #number of encoder chunks to lookback for decoder cross-attention
 
-model = AutoModel(model="paraformer-zh-streaming", model_revision="v2.0.2")
+model = AutoModel(model="paraformer-zh-streaming", model_revision="v2.0.4")
 
 import soundfile
 import os
@@ -121,7 +122,7 @@
 for i in range(total_chunk_num):
     speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride]
     is_final = i == total_chunk_num - 1
-    res = model(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size, encoder_chunk_look_back=encoder_chunk_look_back, decoder_chunk_look_back=decoder_chunk_look_back)
+    res = model.generate(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size, encoder_chunk_look_back=encoder_chunk_look_back, decoder_chunk_look_back=decoder_chunk_look_back)
     print(res)
 ```
 
@@ -131,10 +132,10 @@
 ```python
 from funasr import AutoModel
 
-model = AutoModel(model="fsmn-vad", model_revision="v2.0.2")
+model = AutoModel(model="fsmn-vad", model_revision="v2.0.4")
 
 wav_file = f"{model.model_path}/example/asr_example.wav"
-res = model(input=wav_file)
+res = model.generate(input=wav_file)
 print(res)
 ```
 
@@ -143,7 +144,7 @@
 from funasr import AutoModel
 
 chunk_size = 200 # ms
-model = AutoModel(model="fsmn-vad", model_revision="v2.0.2")
+model = AutoModel(model="fsmn-vad", model_revision="v2.0.4")
 
 import soundfile
 
@@ -156,7 +157,7 @@
 for i in range(total_chunk_num):
     speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride]
     is_final = i == total_chunk_num - 1
-    res = model(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size)
+    res = model.generate(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size)
     if len(res[0]["value"]):
         print(res)
 ```
@@ -165,9 +166,9 @@
 ```python
 from funasr import AutoModel
 
-model = AutoModel(model="ct-punc", model_revision="v2.0.2")
+model = AutoModel(model="ct-punc", model_revision="v2.0.4")
 
-res = model(input="閭ｄ粖澶╃殑浼氬氨鍒拌繖閲屽惂 happy new year 鏄庡勾瑙�")
+res = model.generate(input="閭ｄ粖澶╃殑浼氬氨鍒拌繖閲屽惂 happy new year 鏄庡勾瑙�")
 print(res)
 ```
 
@@ -179,10 +180,10 @@
 
 wav_file = f"{model.model_path}/example/asr_example.wav"
 text_file = f"{model.model_path}/example/text.txt"
-res = model(input=(wav_file, text_file), data_type=("sound", "text"))
+res = model.generate(input=(wav_file, text_file), data_type=("sound", "text"))
 print(res)
 ```
-鏇村璇︾粏鐢ㄦ硶锛圼绀轰緥](examples/industrial_data_pretraining)锛�
+鏇村璇︾粏鐢ㄦ硶锛圼绀轰緥](https://github.com/alibaba-damo-academy/FunASR/tree/main/examples/industrial_data_pretraining)锛�
 
 
 <a name="鏈嶅姟閮ㄧ讲"></a>
@@ -242,4 +243,10 @@
   pages={2063--2067},
   doi={10.21437/Interspeech.2022-9996}
 }
+@article{shi2023seaco,
+  author={Xian Shi and Yexin Yang and Zerui Li and Yanni Chen and Zhifu Gao and Shiliang Zhang},
+  title={{SeACo-Paraformer: A Non-Autoregressive ASR System with Flexible and Effective Hotword Customization Ability}},
+  year=2023,
+  journal={arXiv preprint arXiv:2308.03266(accepted by ICASSP2024)},
+}
 ```

--
Gitblit v1.9.1