Update README

README.md

@@ -1,3 +1,160 @@
 ---
 license: apache-2.0
 ---
+
+# FireRedASR-AED
+
+小红书ASR AED-L版本在AX650N上的部署，原项目地址为：[https://github.com/FireRedTeam/FireRedASR](https://github.com/FireRedTeam/FireRedASR)
+
+转换后的模型放置在axmodel目录，目前支持中文、英文，最长输入10秒的音频。
+
+## 支持平台
+
+- [x] AX650N
+
+
+## 安装依赖
+
+### Python
+
+测试环境为Python 3.12，建议使用[Miniconda](https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-aarch64.sh
+)，安装方法[参考](https://www.anaconda.com/docs/getting-started/miniconda/install#aws-graviton2%2Farm64)
+
+```
+conda create -n fireredasr python=3.12
+conda activate fireredasr
+pip install -r requirements.txt
+```
+
+### 安装pyaxengine
+
+```
+wget https://github.com/AXERA-TECH/pyaxengine/releases/download/0.1.3.rc1/axengine-0.1.3-py3-none-any.whl
+pip install axengine-0.1.3-py3-none-any.whl
+```
+
+
+## 使用
+
+```
+conda activate fireredasr
+python test_ax_model.py
+```
+
+输出结果如下:
+```
+[INFO] Available providers:  ['AxEngineExecutionProvider']
+Namespace(encoder='axmodel/encoder.axmodel', decoder='axmodel/decoder_main.axmodel', cmvn='axmodel/cmvn.ark', dict='axmodel/dict.txt', spm_model='axmodel/train_bpe1000.model', wavlist='wavlist.txt', hypo='hypo_axmodel.txt', beam_size=3, nbest=1, max_len=128)
+[WARNING] Selected provider(s): ['AXCLRTExecutionProvider'] is(are) not available.
+[INFO] Using provider: AxEngineExecutionProvider
+[INFO] Chip type: ChipType.MC50
+[INFO] VNPU type: VNPUType.DISABLED
+[INFO] Engine version: 2.12.0s
+[INFO] Model type: 2 (triple core)
+[INFO] Compiler version: 4.2 9555977e
+load encoder cost 2.764460325241089 seconds
+[WARNING] Selected provider(s): ['AXCLRTExecutionProvider'] is(are) not available.
+[INFO] Using provider: AxEngineExecutionProvider
+[INFO] Model type: 2 (triple core)
+[INFO] Compiler version: 4.2 9555977e
+load decoder_main cost 16.36833119392395 seconds
+[WARNING] Selected provider(s): ['AXCLRTExecutionProvider'] is(are) not available.
+[INFO] Using provider: AxEngineExecutionProvider
+[INFO] Model type: 2 (triple core)
+[INFO] Compiler version: 4.2 9555977e
+load decoder_loop cost 16.194183826446533 seconds
+run encoder take 196.9749927520752ms
+run decoder_main take 130.2931308746338ms
+run decoder_loop take 165.5733585357666ms
+run decoder_loop take 109.67779159545898ms
+run decoder_loop take 101.15742683410645ms
+run decoder_loop take 110.09836196899414ms
+run decoder_loop take 100.29029846191406ms
+run decoder_loop take 109.33351516723633ms
+run decoder_loop take 100.37779808044434ms
+run decoder_loop take 109.72428321838379ms
+run decoder_loop take 100.42023658752441ms
+run decoder_loop take 101.71890258789062ms
+run decoder_loop take 100.09407997131348ms
+run decoder_loop take 110.25619506835938ms
+run decoder_loop take 100.54206848144531ms
+run decoder_loop take 101.93896293640137ms
+['wav/TEST_NET_Y0000000000_-KTKHdZ2fb8_S00000.wav']
+Durations: 1.8
+Transcribe Durations: 2.5527637004852295
+(Real time factor) RTF: 1.4182020558251274
+wav: wav/TEST_NET_Y0000000000_-KTKHdZ2fb8_S00000.wav
+text: 我有的时候说不清楚你们知道吗
+score: -0.9156361222267151
+
+run encoder take 180.2656650543213ms
+run decoder_main take 91.42565727233887ms
+run decoder_loop take 105.18240928649902ms
+run decoder_loop take 100.56614875793457ms
+run decoder_loop take 100.9066104888916ms
+run decoder_loop take 100.9068489074707ms
+run decoder_loop take 102.90265083312988ms
+run decoder_loop take 100.50129890441895ms
+run decoder_loop take 110.12482643127441ms
+run decoder_loop take 100.65031051635742ms
+run decoder_loop take 110.09883880615234ms
+run decoder_loop take 105.48877716064453ms
+run decoder_loop take 100.32439231872559ms
+run decoder_loop take 106.08601570129395ms
+run decoder_loop take 100.79813003540039ms
+run decoder_loop take 100.4643440246582ms
+run decoder_loop take 100.30460357666016ms
+['wav/TEST_MEETING_T0000000001_S00000.wav']
+Durations: 12.369
+Transcribe Durations: 2.464834690093994
+(Real time factor) RTF: 0.19927517908432324
+wav: wav/TEST_MEETING_T0000000001_S00000.wav
+text: 好首先说一下刚才这个
+score: -0.5064160823822021
+
+run encoder take 172.59907722473145ms
+run decoder_main take 91.79949760437012ms
+run decoder_loop take 105.04364967346191ms
+run decoder_loop take 100.62885284423828ms
+run decoder_loop take 101.89318656921387ms
+run decoder_loop take 100.42643547058105ms
+run decoder_loop take 109.7562313079834ms
+['wav/IT0011W0001.wav']
+Durations: 1.992
+Transcribe Durations: 1.0302071571350098
+(Real time factor) RTF: 0.5171722676380571
+wav: wav/IT0011W0001.wav
+text: 换一首歌
+score: -0.016501454636454582
+
+run encoder take 173.07257652282715ms
+run decoder_main take 91.48693084716797ms
+run decoder_loop take 105.42607307434082ms
+run decoder_loop take 100.10981559753418ms
+run decoder_loop take 100.4478931427002ms
+run decoder_loop take 100.23713111877441ms
+run decoder_loop take 100.10337829589844ms
+run decoder_loop take 100.29196739196777ms
+run decoder_loop take 101.7463207244873ms
+run decoder_loop take 100.8148193359375ms
+run decoder_loop take 109.99274253845215ms
+run decoder_loop take 105.45015335083008ms
+run decoder_loop take 100.59380531311035ms
+run decoder_loop take 100.73733329772949ms
+run decoder_loop take 100.4335880279541ms
+run decoder_loop take 109.68661308288574ms
+['wav/BAC009S0764W0121.wav']
+Durations: 4.2039375
+Transcribe Durations: 2.3024709224700928
+(Real time factor) RTF: 0.5476938994621334
+wav: wav/BAC009S0764W0121.wav
+text: 甚至出现交易几乎停滞的情况
+score: -0.11461181938648224
+
+total wav durations: 20.364937500000003
+total transcribe durations: 8.350276470184326
+AVG RTF: 0.4100320204854213
+
+```
+
+```hypo_axmodel.txt```包含识别结果

requirements.txt

@@ -0,0 +1,8 @@
+cn2an>=0.5.23
+kaldiio>=2.18.0
+kaldi_native_fbank>=1.15
+numpy>=1.26.1
+peft>=0.13.2
+sentencepiece
+torch>=2.0.0
+transformers>=4.46.3

test_ax_model.py

@@ -1,7 +1,6 @@
 from fireredasr.data.asr_feat import ASRFeatExtractor
 from fireredasr.tokenizer.aed_tokenizer import ChineseCharEnglishSpmTokenizer
 
-import onnxruntime as ort
 import axengine as axe
 import torch
 import torch.nn.functional as F
@@ -56,12 +55,6 @@ class FireRedASROnnxModel:
         providers=['AXCLRTExecutionProvider', 'AxEngineExecutionProvider'],
         decode_max_len=128
     ):
-        session_opts = ort.SessionOptions()
-        session_opts.inter_op_num_threads = 1
-        session_opts.intra_op_num_threads = 1
-        # session_opts.log_severity_level = 1
-        self.session_opts = session_opts
-        
         # NOTE: 参考whisper设置的最大的解码长度
         # FireRedASR-AED 模型支持的最长语音为 60s
         # ref: https://github.com/FireRedTeam/FireRedASR?tab=readme-ov-file#input-length-limitations
@@ -80,7 +73,6 @@ class FireRedASROnnxModel:
         self.decoder = None
         
         self.init_encoder(encoder_path, providers)
-        # self.init_decoder(decoder_path, providers)
         self.init_decoder_main(decoder_path, providers)
         self.init_decoder_loop(decoder_path, providers)
         self.pe = self.init_pe(decoder_path)
@@ -94,16 +86,6 @@ class FireRedASROnnxModel:
         )
         end_time = time.time()
         logger.info(f"load encoder cost {end_time - start_time} seconds")
-    
-    def init_decoder(self, decoder_path, providers=None):
-        start_time = time.time()
-        self.decoder = ort.InferenceSession(
-            decoder_path,
-            # sess_options=self.session_opts,
-            providers=providers
-        )
-        end_time = time.time()
-        logger.info(f"load decoder cost {end_time - start_time} seconds")
 
     def init_decoder_main(self, decoder_path, providers=None):
         decoder_path = os.path.dirname(decoder_path)