From 4e0aae556bbfb81f765ddb3e247f34441c607c5e Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 21 四月 2023 10:45:16 +0800
Subject: [PATCH] docs

---
 egs_modelscope/vad/TEMPLATE/README.md |    4 ++--
 docs/index.rst                        |    9 ++++++++-
 egs_modelscope/asr/TEMPLATE/README.md |    2 +-
 README.md                             |   13 ++++++-------
 docs/docker.md                        |    2 +-
 5 files changed, 18 insertions(+), 12 deletions(-)

diff --git a/README.md b/README.md
index 29ddd4a..b8e1b89 100644
--- a/README.md
+++ b/README.md
@@ -97,19 +97,18 @@
 ## Citations
 
 ``` bibtex
-@inproceedings{gao2020universal,
-  title={Universal ASR: Unifying Streaming and Non-Streaming ASR Using a Single Encoder-Decoder Model},
-  author={Gao, Zhifu and Zhang, Shiliang and Lei, Ming and McLoughlin, Ian},
-  booktitle={arXiv preprint arXiv:2010.14099},
-  year={2020}
-}
-
 @inproceedings{gao2022paraformer,
   title={Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition},
   author={Gao, Zhifu and Zhang, Shiliang and McLoughlin, Ian and Yan, Zhijie},
   booktitle={INTERSPEECH},
   year={2022}
 }
+@inproceedings{gao2020universal,
+  title={Universal ASR: Unifying Streaming and Non-Streaming ASR Using a Single Encoder-Decoder Model},
+  author={Gao, Zhifu and Zhang, Shiliang and Lei, Ming and McLoughlin, Ian},
+  booktitle={arXiv preprint arXiv:2010.14099},
+  year={2020}
+}
 @inproceedings{Shi2023AchievingTP,
   title={Achieving Timestamp Prediction While Recognizing with Non-Autoregressive End-to-End ASR Model},
   author={Xian Shi and Yanni Chen and Shiliang Zhang and Zhijie Yan},
diff --git a/docs/docker.md b/docs/docker.md
index 95a75f2..77554d3 100644
--- a/docs/docker.md
+++ b/docs/docker.md
@@ -60,6 +60,6 @@
 ```shell
 exit
 sudo docker ps
-sudo docker stop <container-id>
+sudo docker stop funasr
 ```
 
diff --git a/docs/index.rst b/docs/index.rst
index 95c3aa4..2fcc6c6 100644
--- a/docs/index.rst
+++ b/docs/index.rst
@@ -21,9 +21,10 @@
    :caption: Recipe
 
    ./recipe/asr_recipe.md
-   ./recipe/sv_recipe.md
    ./recipe/punc_recipe.md
    ./recipe/vad_recipe.md
+   ./recipe/sv_recipe.md
+   ./recipe/sd_recipe.md
 
 .. toctree::
    :maxdepth: 1
@@ -52,6 +53,12 @@
 
 .. toctree::
    :maxdepth: 1
+   :caption: Huggingface pipeline
+
+   Undo
+
+.. toctree::
+   :maxdepth: 1
    :caption: Runtime
 
    ./runtime/export.md
diff --git a/egs_modelscope/asr/TEMPLATE/README.md b/egs_modelscope/asr/TEMPLATE/README.md
index 7e81f87..3daff1f 100644
--- a/egs_modelscope/asr/TEMPLATE/README.md
+++ b/egs_modelscope/asr/TEMPLATE/README.md
@@ -53,7 +53,7 @@
 rec_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')
 print(rec_result)
 ```
-The decoding mode of `fast` and `normal`
+The decoding mode of `fast` and `normal` is fake streaming, which could be used for evaluating of recognition accuracy.
 Full code of demo, please ref to [demo](https://github.com/alibaba-damo-academy/FunASR/discussions/151)
 #### [RNN-T-online model]()
 Undo
diff --git a/egs_modelscope/vad/TEMPLATE/README.md b/egs_modelscope/vad/TEMPLATE/README.md
index 84601b0..df45b35 100644
--- a/egs_modelscope/vad/TEMPLATE/README.md
+++ b/egs_modelscope/vad/TEMPLATE/README.md
@@ -45,7 +45,7 @@
 
 #### API-reference
 ##### Define pipeline
-- `task`: `Tasks.auto_speech_recognition`
+- `task`: `Tasks.voice_activity_detection`
 - `model`: model name in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_models.html#pretrained-models-on-modelscope), or model path in local disk
 - `ngpu`: `1` (Defalut), decoding on GPU. If ngpu=0, decoding on CPU
 - `ncpu`: `1` (Defalut), sets the number of threads used for intraop parallelism on CPU 
@@ -67,7 +67,7 @@
 - `output_dir`: None (Defalut), the output path of results if set
 
 ### Inference with multi-thread CPUs or multi GPUs
-FunASR also offer recipes [infer.sh](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs_modelscope/asr/TEMPLATE/infer.sh) to decode with multi-thread CPUs, or multi GPUs.
+FunASR also offer recipes [infer.sh](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs_modelscope/vad/TEMPLATE/infer.sh) to decode with multi-thread CPUs, or multi GPUs.
 
 - Setting parameters in `infer.sh`
     - `model`: model name in [model zoo](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_models.html#pretrained-models-on-modelscope), or model path in local disk

--
Gitblit v1.9.1