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.md |   24 ++++++++++++++----------
 1 files changed, 14 insertions(+), 10 deletions(-)

diff --git a/README.md b/README.md
index 2bd28e2..1e3707c 100644
--- a/README.md
+++ b/README.md
@@ -91,12 +91,13 @@
 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")
+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=64, 
+                     batch_size_s=300, 
                      hotword='榄旀惌')
 print(res)
 ```
@@ -110,7 +111,7 @@
 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
@@ -133,7 +134,7 @@
 ```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.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
 
@@ -164,7 +165,7 @@
 ```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.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)
 ```
@@ -172,12 +173,15 @@
 ```python
 from funasr import AutoModel
 
-model = AutoModel(model="fa-zh", model_revision="v2.0.2")
+model = AutoModel(model="fa-zh", model_revision="v2.0.4")
 wav_file = f"{model.model_path}/example/asr_example.wav"
 text_file = f"{model.model_path}/example/text.txt"
 res = model.generate(input=(wav_file, text_file), data_type=("sound", "text"))
 print(res)
 ```
+
+More examples ref to [docs](https://github.com/alibaba-damo-academy/FunASR/tree/main/examples/industrial_data_pretraining)
+
 [//]: # (FunASR supports inference and fine-tuning of models trained on industrial datasets of tens of thousands of hours. For more details, please refer to &#40;[modelscope_egs]&#40;https://alibaba-damo-academy.github.io/FunASR/en/modelscope_pipeline/quick_start.html&#41;&#41;. It also supports training and fine-tuning of models on academic standard datasets. For more details, please refer to&#40;[egs]&#40;https://alibaba-damo-academy.github.io/FunASR/en/academic_recipe/asr_recipe.html&#41;&#41;. The models include speech recognition &#40;ASR&#41;, speech activity detection &#40;VAD&#41;, punctuation recovery, language model, speaker verification, speaker separation, and multi-party conversation speech recognition. For a detailed list of models, please refer to the [Model Zoo]&#40;https://github.com/alibaba-damo-academy/FunASR/blob/main/docs/model_zoo/modelscope_models.md&#41;:)
 
 ## Deployment Service

--
Gitblit v1.9.1