From 41e4b59033cc0d627b2e244f0e2d602a43d91126 Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 10 二月 2023 18:55:35 +0800
Subject: [PATCH] Merge pull request #94 from alibaba-damo-academy/gzf

---
 funasr/export/export_model.py |   63 ++++++++++++++++---------------
 1 files changed, 33 insertions(+), 30 deletions(-)

diff --git a/funasr/export/export_model.py b/funasr/export/export_model.py
index 9a599eb..239fd6c 100644
--- a/funasr/export/export_model.py
+++ b/funasr/export/export_model.py
@@ -1,3 +1,4 @@
+import json
 from typing import Union, Dict
 from pathlib import Path
 from typeguard import check_argument_types
@@ -8,14 +9,15 @@
 
 from funasr.bin.asr_inference_paraformer import Speech2Text
 from funasr.export.models import get_model
-
-
+import numpy as np
+import random
 
 class ASRModelExportParaformer:
     def __init__(self, cache_dir: Union[Path, str] = None, onnx: bool = True):
         assert check_argument_types()
+        self.set_all_random_seed(0)
         if cache_dir is None:
-            cache_dir = Path.home() / "cache" / "export"
+            cache_dir = Path.home() / ".cache" / "export"
 
         self.cache_dir = Path(cache_dir)
         self.export_config = dict(
@@ -24,8 +26,9 @@
         )
         logging.info("output dir: {}".format(self.cache_dir))
         self.onnx = onnx
+        
 
-    def export(
+    def _export(
         self,
         model: Speech2Text,
         tag_name: str = None,
@@ -60,38 +63,38 @@
         model_script = torch.jit.trace(model, dummy_input)
         model_script.save(os.path.join(path, f'{model.model_name}.torchscripts'))
 
-    def export_from_modelscope(
-        self,
-        tag_name: str = 'damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch',
-    ):
+    def set_all_random_seed(self, seed: int):
+        random.seed(seed)
+        np.random.seed(seed)
+        torch.random.manual_seed(seed)
+    def export(self,
+               tag_name: str = 'damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch',
+               mode: str = 'paraformer',
+               ):
         
-        from funasr.tasks.asr import ASRTaskParaformer as ASRTask
-        from modelscope.hub.snapshot_download import snapshot_download
-
-        model_dir = snapshot_download(tag_name, cache_dir=self.cache_dir)
-        asr_train_config = os.path.join(model_dir, 'config.yaml')
-        asr_model_file = os.path.join(model_dir, 'model.pb')
-        cmvn_file = os.path.join(model_dir, 'am.mvn')
-        model, asr_train_args = ASRTask.build_model_from_file(
-            asr_train_config, asr_model_file, cmvn_file, 'cpu'
-        )
-        self.export(model, tag_name)
-
-    def export_from_local(
-        self,
-        tag_name: str = '/root/cache/export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch',
-    ):
-    
-        from funasr.tasks.asr import ASRTaskParaformer as ASRTask
-    
         model_dir = tag_name
+        if model_dir.startswith('damo/'):
+            from modelscope.hub.snapshot_download import snapshot_download
+            model_dir = snapshot_download(model_dir, cache_dir=self.cache_dir)
         asr_train_config = os.path.join(model_dir, 'config.yaml')
         asr_model_file = os.path.join(model_dir, 'model.pb')
         cmvn_file = os.path.join(model_dir, 'am.mvn')
+        json_file = os.path.join(model_dir, 'configuration.json')
+        if mode is None:
+            import json
+            with open(json_file, 'r') as f:
+                config_data = json.load(f)
+                mode = config_data['model']['model_config']['mode']
+        if mode == 'paraformer':
+            from funasr.tasks.asr import ASRTaskParaformer as ASRTask
+        elif mode == 'uniasr':
+            from funasr.tasks.asr import ASRTaskUniASR as ASRTask
+            
         model, asr_train_args = ASRTask.build_model_from_file(
             asr_train_config, asr_model_file, cmvn_file, 'cpu'
         )
-        self.export(model, tag_name)
+        self._export(model, tag_name)
+            
 
     def _export_onnx(self, model, verbose, path, enc_size=None):
         if enc_size:
@@ -116,5 +119,5 @@
 if __name__ == '__main__':
     output_dir = "../export"
     export_model = ASRModelExportParaformer(cache_dir=output_dir, onnx=False)
-    export_model.export_from_modelscope('damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch')
-    # export_model.export_from_local('/root/cache/export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch')
\ No newline at end of file
+    export_model.export('damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch')
+    # export_model.export('/root/cache/export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch')
\ No newline at end of file

--
Gitblit v1.9.1