From 9fcb3cc06b4e324f0913d2f61b89becc2baeef1b Mon Sep 17 00:00:00 2001
From: hnluo <haoneng.lhn@alibaba-inc.com>
Date: 星期一, 11 九月 2023 17:40:03 +0800
Subject: [PATCH] Merge pull request #932 from alibaba-damo-academy/dev_lhn

---
 funasr/bin/asr_inference_launch.py |   19 ++++++++++++++++++-
 1 files changed, 18 insertions(+), 1 deletions(-)

diff --git a/funasr/bin/asr_inference_launch.py b/funasr/bin/asr_inference_launch.py
index 0fd5abd..6fa57a7 100644
--- a/funasr/bin/asr_inference_launch.py
+++ b/funasr/bin/asr_inference_launch.py
@@ -236,6 +236,7 @@
         timestamp_infer_config: Union[Path, str] = None,
         timestamp_model_file: Union[Path, str] = None,
         param_dict: dict = None,
+        decoding_ind: int = 0,
         **kwargs,
 ):
     ncpu = kwargs.get("ncpu", 1)
@@ -290,6 +291,7 @@
         nbest=nbest,
         hotword_list_or_file=hotword_list_or_file,
         clas_scale=clas_scale,
+        decoding_ind=decoding_ind,
     )
 
     speech2text = Speech2TextParaformer(**speech2text_kwargs)
@@ -312,6 +314,7 @@
             **kwargs,
     ):
 
+        decoding_ind = None
         hotword_list_or_file = None
         if param_dict is not None:
             hotword_list_or_file = param_dict.get('hotword')
@@ -319,6 +322,8 @@
             hotword_list_or_file = kwargs['hotword']
         if hotword_list_or_file is not None or 'hotword' in kwargs:
             speech2text.hotword_list = speech2text.generate_hotwords_list(hotword_list_or_file)
+        if param_dict is not None and "decoding_ind" in param_dict:
+            decoding_ind = param_dict["decoding_ind"]
 
         # 3. Build data-iterator
         if data_path_and_name_and_type is None and raw_inputs is not None:
@@ -365,6 +370,7 @@
             # N-best list of (text, token, token_int, hyp_object)
 
             time_beg = time.time()
+            batch["decoding_ind"] = decoding_ind
             results = speech2text(**batch)
             if len(results) < 1:
                 hyp = Hypothesis(score=0.0, scores={}, states={}, yseq=[])
@@ -1290,6 +1296,7 @@
         quantize_dtype: Optional[str] = "float16",
         streaming: Optional[bool] = False,
         simu_streaming: Optional[bool] = False,
+        full_utt: Optional[bool] = False,
         chunk_size: Optional[int] = 16,
         left_context: Optional[int] = 16,
         right_context: Optional[int] = 0,
@@ -1366,6 +1373,7 @@
         quantize_dtype=quantize_dtype,
         streaming=streaming,
         simu_streaming=simu_streaming,
+        full_utt=full_utt,
         chunk_size=chunk_size,
         left_context=left_context,
         right_context=right_context,
@@ -1416,7 +1424,7 @@
                         _end = (i + 1) * speech2text._ctx
 
                         speech2text.streaming_decode(
-                            speech[i * speech2text._ctx: _end], is_final=False
+                            speech[i * speech2text._ctx: _end + speech2text._right_ctx], is_final=False
                         )
 
                     final_hyps = speech2text.streaming_decode(
@@ -1424,6 +1432,8 @@
                     )
                 elif speech2text.simu_streaming:
                     final_hyps = speech2text.simu_streaming_decode(**batch)
+                elif speech2text.full_utt:
+                    final_hyps = speech2text.full_utt_decode(**batch)
                 else:
                     final_hyps = speech2text(**batch)
 
@@ -1782,6 +1792,12 @@
         default=1,
         help="The batch size for inference",
     )
+    group.add_argument(
+        "--decoding_ind",
+        type=int,
+        default=0,
+        help="chunk select for chunk encoder",
+    )
     group.add_argument("--nbest", type=int, default=5, help="Output N-best hypotheses")
     group.add_argument("--beam_size", type=int, default=20, help="Beam size")
     group.add_argument("--penalty", type=float, default=0.0, help="Insertion penalty")
@@ -1812,6 +1828,7 @@
     group.add_argument("--ngram_weight", type=float, default=0.9, help="ngram weight")
     group.add_argument("--streaming", type=str2bool, default=False)
     group.add_argument("--simu_streaming", type=str2bool, default=False)
+    group.add_argument("--full_utt", type=str2bool, default=False)
     group.add_argument("--chunk_size", type=int, default=16)
     group.add_argument("--left_context", type=int, default=16)
     group.add_argument("--right_context", type=int, default=0)

--
Gitblit v1.9.1