From 9777fdec3959a7d56dd8ae03d0f4170969500cf7 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 18 四月 2023 13:21:41 +0800
Subject: [PATCH] docs
---
docs/vad_recipe.md | 2 +-
docs/sv_recipe.md | 2 +-
docs/papers.md | 4 ++--
docs/index.rst | 20 ++++++++++++++------
docs/punc_recipe.md | 2 +-
docs/asr_recipe.md | 2 +-
6 files changed, 20 insertions(+), 12 deletions(-)
diff --git a/docs/get_started.md b/docs/asr_recipe.md
similarity index 99%
copy from docs/get_started.md
copy to docs/asr_recipe.md
index 4a7d86e..f82a6fe 100644
--- a/docs/get_started.md
+++ b/docs/asr_recipe.md
@@ -1,4 +1,4 @@
-# Get Started
+# Speech Recognition
Here we take "Training a paraformer model from scratch using the AISHELL-1 dataset" as an example to introduce how to use FunASR. According to this example, users can similarly employ other datasets (such as AISHELL-2 dataset, etc.) to train other models (such as conformer, transformer, etc.).
## Overall Introduction
diff --git a/docs/index.rst b/docs/index.rst
index 7bf22b5..ae75c3f 100644
--- a/docs/index.rst
+++ b/docs/index.rst
@@ -11,20 +11,28 @@
.. toctree::
:maxdepth: 1
- :caption: Installation:
+ :caption: Installation
./installation.md
.. toctree::
:maxdepth: 1
- :caption: Tutorial:
+ :caption: Recipe
- ./get_started.md
+ ./asr_recipe.md
+ ./sv_recipe.md
+ ./punc_recipe.md
+ ./vad_recipe.md
+
+.. toctree::
+ :maxdepth: 1
+ :caption: Define Model
+
./build_task.md
.. toctree::
:maxdepth: 1
- :caption: Runtime:
+ :caption: Runtime
./export.md
./onnxruntime_python.md
@@ -38,14 +46,14 @@
.. toctree::
:maxdepth: 1
- :caption: ModelScope pipeline:
+ :caption: ModelScope pipeline
./modelscope_models.md
./modelscope_usages.md
.. toctree::
:maxdepth: 1
- :caption: Papers:
+ :caption: Papers
./papers.md
diff --git a/docs/papers.md b/docs/papers.md
index f119dad..33bf72f 100644
--- a/docs/papers.md
+++ b/docs/papers.md
@@ -2,7 +2,7 @@
FunASR have implemented the following paper code
-### Speech Recognition Models
+### Speech Recognition
- [Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition](https://arxiv.org/abs/2206.08317), INTERSPEECH 2022.
- [Universal ASR: Unifying Streaming and Non-Streaming ASR Using a Single Encoder-Decoder Model](https://arxiv.org/abs/2010.14099), arXiv preprint arXiv:2010.14099, 2020.
- [San-m: Memory equipped self-attention for end-to-end speech recognition](https://arxiv.org/pdf/2006.01713), INTERSPEECH 2020
@@ -11,7 +11,7 @@
- [Sequence-to-sequence learning with Transducers](https://arxiv.org/pdf/1211.3711.pdf), NIPS 2016
-### Multi-talker Speech Recognition Models
+### Multi-talker Speech Recognition
- [MFCCA:Multi-Frame Cross-Channel attention for multi-speaker ASR in Multi-party meeting scenario](https://arxiv.org/abs/2210.05265), ICASSP 2022
### Voice Activity Detection
diff --git a/docs/get_started.md b/docs/punc_recipe.md
similarity index 99%
copy from docs/get_started.md
copy to docs/punc_recipe.md
index 4a7d86e..0306cd3 100644
--- a/docs/get_started.md
+++ b/docs/punc_recipe.md
@@ -1,4 +1,4 @@
-# Get Started
+# Punctuation Restoration
Here we take "Training a paraformer model from scratch using the AISHELL-1 dataset" as an example to introduce how to use FunASR. According to this example, users can similarly employ other datasets (such as AISHELL-2 dataset, etc.) to train other models (such as conformer, transformer, etc.).
## Overall Introduction
diff --git a/docs/get_started.md b/docs/sv_recipe.md
similarity index 99%
rename from docs/get_started.md
rename to docs/sv_recipe.md
index 4a7d86e..0eebe3d 100644
--- a/docs/get_started.md
+++ b/docs/sv_recipe.md
@@ -1,4 +1,4 @@
-# Get Started
+# Speaker Verification
Here we take "Training a paraformer model from scratch using the AISHELL-1 dataset" as an example to introduce how to use FunASR. According to this example, users can similarly employ other datasets (such as AISHELL-2 dataset, etc.) to train other models (such as conformer, transformer, etc.).
## Overall Introduction
diff --git a/docs/get_started.md b/docs/vad_recipe.md
similarity index 99%
copy from docs/get_started.md
copy to docs/vad_recipe.md
index 4a7d86e..6aa7532 100644
--- a/docs/get_started.md
+++ b/docs/vad_recipe.md
@@ -1,4 +1,4 @@
-# Get Started
+# Voice Activity Detection
Here we take "Training a paraformer model from scratch using the AISHELL-1 dataset" as an example to introduce how to use FunASR. According to this example, users can similarly employ other datasets (such as AISHELL-2 dataset, etc.) to train other models (such as conformer, transformer, etc.).
## Overall Introduction
--
Gitblit v1.9.1