From 579afd6ac81570438c7e95164333155a9cca163c Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 14 七月 2023 19:03:15 +0800
Subject: [PATCH] docs and GPU memory release
---
funasr/version.txt | 2 +-
funasr/bin/vad_inference_launch.py | 2 +-
README_zh.md | 2 +-
funasr/bin/asr_inference_launch.py | 2 ++
README.md | 17 +++++++++++------
5 files changed, 16 insertions(+), 9 deletions(-)
diff --git a/README.md b/README.md
index 3fbbbb4..46741fa 100644
--- a/README.md
+++ b/README.md
@@ -14,13 +14,13 @@
[**News**](https://github.com/alibaba-damo-academy/FunASR#whats-new)
| [**Highlights**](#highlights)
| [**Installation**](#installation)
-| [**Usage**](#usage)
-| [**Papers**](https://github.com/alibaba-damo-academy/FunASR#citations)
-| [**Runtime**](https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/runtime)
-| [**Model Zoo**](https://github.com/alibaba-damo-academy/FunASR/blob/main/docs/model_zoo/modelscope_models.md)
+| [**Quick Start**](#quick-start)
+| [**Runtime**](./funasr/runtime/readme.md)
+| [**Model Zoo**](./docs/model_zoo/modelscope_models.md)
| [**Contact**](#contact)
-| [**M2MET2.0 Challenge**](https://github.com/alibaba-damo-academy/FunASR#multi-channel-multi-party-meeting-transcription-20-m2met20-challenge)
+
+<a name="whats-new"></a>
## What's new:
### FunASR runtime-SDK
@@ -36,11 +36,13 @@
For the release notes, please ref to [news](https://github.com/alibaba-damo-academy/FunASR/releases)
+<a name="highlights"></a>
## Highlights
- FunASR is a fundamental speech recognition toolkit that offers a variety of features, including speech recognition (ASR), Voice Activity Detection (VAD), Punctuation Restoration, Language Models, Speaker Verification, Speaker diarization and multi-talker ASR.
- We have released a vast collection of academic and industrial pretrained models on the [ModelScope](https://www.modelscope.cn/models?page=1&tasks=auto-speech-recognition), which can be accessed through our [Model Zoo](https://github.com/alibaba-damo-academy/FunASR/blob/main/docs/model_zoo/modelscope_models.md). The representative [Paraformer-large](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) model has achieved SOTA performance in many speech recognition tasks.
- FunASR offers a user-friendly pipeline for fine-tuning pretrained models from the [ModelScope](https://www.modelscope.cn/models?page=1&tasks=auto-speech-recognition). Additionally, the optimized dataloader in FunASR enables faster training speeds for large-scale datasets. This feature enhances the efficiency of the speech recognition process for researchers and practitioners.
+<a name="Installation"></a>
## Installation
Install from pip
@@ -70,7 +72,8 @@
For more details, please ref to [installation](https://alibaba-damo-academy.github.io/FunASR/en/installation/installation.html)
-## Usage
+<a name="quick-start"></a>
+## Quick Start
You could use FunASR by:
@@ -120,6 +123,8 @@
#python funasr_wss_client.py --host "127.0.0.1" --port 10095 --mode 2pass --chunk_size "8,8,4" --audio_in "./data/wav.scp" --output_dir "./results"
```
More examples could be found in [docs](https://alibaba-damo-academy.github.io/FunASR/en/runtime/websocket_python.html#id2)
+
+<a name="contact"></a>
## Contact
If you have any questions about FunASR, please contact us by
diff --git a/README_zh.md b/README_zh.md
index eb9005b..ef5cfa6 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -201,7 +201,7 @@
## 璁稿彲鍗忚
-椤圭洰閬靛惊[The MIT License](https://opensource.org/licenses/MIT)寮�婧愬崗璁�. 宸ヤ笟妯″瀷璁稿彲鍗忚璇峰弬鑰冿紙[鐐瑰嚮姝ゅ](./MODEL_LICENSE)锛�
+椤圭洰閬靛惊[The MIT License](https://opensource.org/licenses/MIT)寮�婧愬崗璁�� 宸ヤ笟妯″瀷璁稿彲鍗忚璇峰弬鑰冿紙[鐐瑰嚮姝ゅ](./MODEL_LICENSE)锛�
## Stargazers over time
diff --git a/funasr/bin/asr_inference_launch.py b/funasr/bin/asr_inference_launch.py
index 701379a..3ad0891 100644
--- a/funasr/bin/asr_inference_launch.py
+++ b/funasr/bin/asr_inference_launch.py
@@ -439,6 +439,7 @@
logging.info(rtf_avg)
if writer is not None:
ibest_writer["rtf"]["rtf_avf"] = rtf_avg
+ torch.cuda.empty_cache()
return asr_result_list
return _forward
@@ -730,6 +731,7 @@
ibest_writer["time_stamp"][key] = "{}".format(time_stamp_postprocessed)
logging.info("decoding, utt: {}, predictions: {}".format(key, text_postprocessed_punc))
+ torch.cuda.empty_cache()
return asr_result_list
return _forward
diff --git a/funasr/bin/vad_inference_launch.py b/funasr/bin/vad_inference_launch.py
index 47af011..0cde570 100644
--- a/funasr/bin/vad_inference_launch.py
+++ b/funasr/bin/vad_inference_launch.py
@@ -123,7 +123,7 @@
vad_results.append(item)
if writer is not None:
ibest_writer["text"][keys[i]] = "{}".format(results[i])
-
+ torch.cuda.empty_cache()
return vad_results
return _forward
diff --git a/funasr/version.txt b/funasr/version.txt
index 1a5ac0d..faef31a 100644
--- a/funasr/version.txt
+++ b/funasr/version.txt
@@ -1 +1 @@
-0.6.9
+0.7.0
--
Gitblit v1.9.1