From 55c09aeaa25b4bb88a50e09ba68fa6ff00a6d676 Mon Sep 17 00:00:00 2001
From: shixian.shi <shixian.shi@alibaba-inc.com>
Date: 星期一, 15 一月 2024 20:10:39 +0800
Subject: [PATCH] update readme, fix seaco bug

---
 README.md |   38 +++++++++++++++-----------------------
 1 files changed, 15 insertions(+), 23 deletions(-)

diff --git a/README.md b/README.md
index 50ca183..05f6364 100644
--- a/README.md
+++ b/README.md
@@ -90,12 +90,15 @@
 ### Speech Recognition (Non-streaming)
 ```python
 from funasr import AutoModel
-
-model = AutoModel(model="paraformer-zh")
-# for the long duration wav, you could add vad model
-# model = AutoModel(model="paraformer-zh", vad_model="fsmn-vad", punc_model="ct-punc")
-
-res = model(input="asr_example_zh.wav", batch_size=64)
+# 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=16, 
+            hotword='榄旀惌')
 print(res)
 ```
 Note: `model_hub`: represents the model repository, `ms` stands for selecting ModelScope download, `hf` stands for selecting Huggingface download.
@@ -108,7 +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="v2.0.0")
+model = AutoModel(model="paraformer-zh-streaming", model_revision="v2.0.2")
 
 import soundfile
 import os
@@ -122,13 +125,7 @@
 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(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)
 ```
 Note: `chunk_size` is the configuration for streaming latency.` [0,10,5]` indicates that the real-time display granularity is `10*60=600ms`, and the lookahead information is `5*60=300ms`. Each inference input is `600ms` (sample points are `16000*0.6=960`), and the output is the corresponding text. For the last speech segment input, `is_final=True` needs to be set to force the output of the last word.
@@ -161,11 +158,7 @@
 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(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size)
     if len(res[0]["value"]):
         print(res)
 ```
@@ -173,7 +166,7 @@
 ```python
 from funasr import AutoModel
 
-model = AutoModel(model="ct-punc", model_revision="v2.0.1")
+model = AutoModel(model="ct-punc", model_revision="v2.0.2")
 
 res = model(input="閭ｄ粖澶╃殑浼氬氨鍒拌繖閲屽惂 happy new year 鏄庡勾瑙�")
 print(res)
@@ -182,12 +175,11 @@
 ```python
 from funasr import AutoModel
 
-model = AutoModel(model="fa-zh", model_revision="v2.0.0")
+model = AutoModel(model="fa-zh", model_revision="v2.0.2")
 
 wav_file = f"{model.model_path}/example/asr_example.wav"
 text_file = f"{model.model_path}/example/asr_example.wav"
-res = model(input=(wav_file, text_file),
-            data_type=("sound", "text"))
+res = model(input=(wav_file, text_file), data_type=("sound", "text"))
 print(res)
 ```
 [//]: # (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;:)

--
Gitblit v1.9.1