[ASR] add wav2vec2 aishell model result, test=asr (#3012)

* Create RESULT.md

* add wav2vec2ASR-large-aishell1 finetune model.

* update model link and add readme.

* fix released model info.

README.md

@@ -178,6 +178,7 @@ Via the easy-to-use, efficient, flexible and scalable implementation, our vision
   - 🧩  *Cascaded models application*: as an extension of the typical traditional audio tasks, we combine the workflows of the aforementioned tasks with other fields like Natural language processing (NLP) and Computer Vision (CV).
 
 ### Recent Update
+- 👑 2023.03.09: Add [Wav2vec2ASR-zh](./examples/aishell/asr3).
 - 🎉 2023.03.07: Add [TTS ARM Linux C++ Demo](./demos/TTSArmLinux).
 - 🎉 2023.02.16: Add [Cantonese TTS](./examples/canton/tts3).
 - 🔥 2023.01.10: Add [code-switch asr CLI and Demos](./demos/speech_recognition).

README_cn.md

@@ -183,6 +183,7 @@
   - 🧩 级联模型应用: 作为传统语音任务的扩展，我们结合了自然语言处理、计算机视觉等任务，实现更接近实际需求的产业级应用。
 
 ### 近期更新
+- 👑 2023.03.09: 新增 [Wav2vec2ASR-zh](./examples/aishell/asr3).
 - 🎉 2023.03.07: 新增 [TTS ARM Linux C++ 部署示例](./demos/TTSArmLinux)。
 - 🎉 2023.02.16: 新增[粤语语音合成](./examples/canton/tts3)。
 - 🔥 2023.01.10: 新增[中英混合 ASR CLI 和 Demos](./demos/speech_recognition)。

docs/source/released_model.md

@@ -25,7 +25,7 @@ Model | Pre-Train Method | Pre-Train Data | Finetune Data | Size | Descriptions
 [Wav2vec2-large-960h-lv60-self Model](https://paddlespeech.bj.bcebos.com/wav2vec/wav2vec2-large-960h-lv60-self.pdparams) | wav2vec2 | Librispeech and LV-60k Dataset (5.3w h) | - | 1.18 GB |Pre-trained Wav2vec2.0 Model | - | - | - | 
 [Wav2vec2ASR-large-960h-librispeech Model](https://paddlespeech.bj.bcebos.com/s2t/librispeech/asr3/wav2vec2ASR-large-960h-librispeech_ckpt_1.3.1.model.tar.gz) | wav2vec2 | Librispeech and LV-60k Dataset (5.3w h) | Librispeech (960 h) | 718 MB |Encoder: Wav2vec2.0, Decoder: CTC, Decoding method: Greedy search | - | 0.0189 | [Wav2vecASR Librispeech ASR3](../../examples/librispeech/asr3) |
 [Wav2vec2-large-wenetspeech-self Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr3/wav2vec2-large-wenetspeech-self_ckpt_1.3.0.model.tar.gz) | wav2vec2 | Wenetspeech Dataset (1w h) | - | 714 MB |Pre-trained Wav2vec2.0 Model | - | - | - | 
-[Wav2vec2ASR-large-aishell1 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr3/wav2vec2ASR-large-aishell1_ckpt_1.3.0.model.tar.gz) | wav2vec2 | Wenetspeech Dataset (1w h) | aishell1 (train set) | 1.17 GB |Encoder: Wav2vec2.0, Decoder: CTC, Decoding method: Greedy search | 0.0453 | - | - |
+[Wav2vec2ASR-large-aishell1 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr3/wav2vec2ASR-large-aishell1_ckpt_1.4.0.model.tar.gz) | wav2vec2 | Wenetspeech Dataset (1w h) | aishell1 (train set) | 1.18 GB |Encoder: Wav2vec2.0, Decoder: CTC, Decoding method: Greedy search | 0.0510 | - | - |
 
 ### Whisper Model
 Demo Link | Training Data | Size | Descriptions | CER | Model 

examples/aishell/asr3/README.md

@@ -164,8 +164,8 @@ using the `tar` scripts to unpack the model and then you can use the script to t
 
 For example:
 ```bash
-wget https://paddlespeech.bj.bcebos.com/s2t/aishell/asr3/wav2vec2ASR-large-aishell1_ckpt_1.3.0.model.tar.gz
-tar xzvf wav2vec2ASR-large-aishell1_ckpt_1.3.0.model.tar.gz
+wget https://paddlespeech.bj.bcebos.com/s2t/aishell/asr3/wav2vec2ASR-large-aishell1_ckpt_1.4.0.model.tar.gz
+tar xzvf wav2vec2ASR-large-aishell1_ckpt_1.4.0.model.tar.gz
 source path.sh
 # If you have process the data and get the manifest file， you can skip the following 2 steps
 bash local/data.sh --stage -1 --stop_stage -1
@@ -185,8 +185,8 @@ In some situations, you want to use the trained model to do the inference for th
 ```
 you can train the model by yourself using ```bash run.sh --stage 0 --stop_stage 3```, or you can download the pretrained model through the script below:
 ```bash
-wget https://paddlespeech.bj.bcebos.com/s2t/aishell/asr3/wav2vec2ASR-large-aishell1_ckpt_1.3.0.model.tar.gz
-tar xzvf wav2vec2ASR-large-aishell1_ckpt_1.3.0.model.tar.gz
+wget https://paddlespeech.bj.bcebos.com/s2t/aishell/asr3/wav2vec2ASR-large-aishell1_ckpt_1.4.0.model.tar.gz
+tar xzvf wav2vec2ASR-large-aishell1_ckpt_1.4.0.model.tar.gz
 ```
 You can download the audio demo:
 ```bash

examples/aishell/asr3/RESULT.md

+# AISHELL
+
+## Version
+
+* paddle version: develop (commit id: daea892c67e85da91906864de40ce9f6f1b893ae)
+* paddlespeech version: develop (commit id: c14b4238b256693281e59605abff7c9435b3e2b2)
+
+## Device
+* python: 3.7
+* cuda: 10.2
+* cudnn: 7.6
+
+## Result
+train: Epoch 80, 2*V100-32G, batchsize:5
+| Model | Params | Config | Augmentation| Test set | Decode method | WER |  
+| --- | --- | --- | --- | --- | --- | --- |
+| wav2vec2ASR | 324.49 M | conf/wav2vec2ASR.yaml | spec_aug | test-set | greedy search | 5.1009 |  

paddlespeech/resource/pretrained_models.py

@@ -103,6 +103,22 @@ ssl_dynamic_pretrained_models = {
             'exp/wav2vec2ASR/checkpoints/avg_1.pdparams',
         },
     },
+    "wav2vec2ASR_aishell1-zh-16k": {
+        '1.4': {
+            'url':
+            'https://paddlespeech.bj.bcebos.com/s2t/aishell/asr3/wav2vec2ASR-large-aishell1_ckpt_1.4.0.model.tar.gz',
+            'md5':
+            '9f0bc943adb822789bf61e674b229d17',
+            'cfg_path':
+            'model.yaml',
+            'ckpt_path':
+            'exp/wav2vec2ASR/checkpoints/avg_1',
+            'model':
+            'exp/wav2vec2ASR/checkpoints/avg_1.pdparams',
+            'params':
+            'exp/wav2vec2ASR/checkpoints/avg_1.pdparams',
+        },
+    },
 }
 
 # ---------------------------------
@@ -1644,8 +1660,8 @@ tts_static_pretrained_models["pwgan_male-en"] = tts_static_pretrained_models[
     "pwgan_male-mix"] = tts_static_pretrained_models["pwgan_male-zh"]
 tts_static_pretrained_models["hifigan_male-en"] = tts_static_pretrained_models[
     "hifigan_male-mix"] = tts_static_pretrained_models["hifigan_male-zh"]
-tts_static_pretrained_models["pwgan_aishell3-canton"] = tts_static_pretrained_models[
-    "pwgan_aishell3-zh"]
+tts_static_pretrained_models[
+    "pwgan_aishell3-canton"] = tts_static_pretrained_models["pwgan_aishell3-zh"]
 
 tts_onnx_pretrained_models = {
     # speedyspeech
@@ -1979,8 +1995,9 @@ tts_onnx_pretrained_models["pwgan_male_onnx-en"] = tts_onnx_pretrained_models[
 tts_onnx_pretrained_models["hifigan_male_onnx-en"] = tts_onnx_pretrained_models[
     "hifigan_male_onnx-mix"] = tts_onnx_pretrained_models[
         "hifigan_male_onnx-zh"]
-tts_onnx_pretrained_models["pwgan_aishell3_onnx-canton"] = tts_onnx_pretrained_models[
-    "pwgan_aishell3_onnx-zh"]
+tts_onnx_pretrained_models[
+    "pwgan_aishell3_onnx-canton"] = tts_onnx_pretrained_models[
+        "pwgan_aishell3_onnx-zh"]
 
 # ---------------------------------
 # ------------ Vector -------------
@@ -2058,10 +2075,10 @@ rhy_frontend_models = {
 # ---------------------------------
 
 StarGANv2VC_source = {
-    '1.0' :{
-        'url': 'https://paddlespeech.bj.bcebos.com/Parakeet/released_models/starganv2vc/StarGANv2VC_source.zip',
-        'md5': '195e169419163f5648030ba84c71f866',
-
+    '1.0': {
+        'url':
+        'https://paddlespeech.bj.bcebos.com/Parakeet/released_models/starganv2vc/StarGANv2VC_source.zip',
+        'md5':
+        '195e169419163f5648030ba84c71f866',
     }
 }
-