From a5cd4bb473b19fe2af1753fa7e60a997a8208447 Mon Sep 17 00:00:00 2001
From: aky15 <ankeyu.aky@11.17.44.249>
Date: 星期一, 14 八月 2023 10:54:23 +0800
Subject: [PATCH] support offline inference for unified streaming/non-streaming rnnt

---
 funasr/bin/asr_infer.py            |   34 ++++++++++++++++++++++++++++++++++
 funasr/bin/asr_inference_launch.py |    6 +++++-
 2 files changed, 39 insertions(+), 1 deletions(-)

diff --git a/funasr/bin/asr_infer.py b/funasr/bin/asr_infer.py
index 02ca63d..2e002b7 100644
--- a/funasr/bin/asr_infer.py
+++ b/funasr/bin/asr_infer.py
@@ -1336,6 +1336,7 @@
             nbest: int = 1,
             streaming: bool = False,
             simu_streaming: bool = False,
+            full_utt: bool = False,
             chunk_size: int = 16,
             left_context: int = 32,
             right_context: int = 0,
@@ -1430,6 +1431,7 @@
         self.beam_search = beam_search
         self.streaming = streaming
         self.simu_streaming = simu_streaming
+        self.full_utt = full_utt
         self.chunk_size = max(chunk_size, 0)
         self.left_context = left_context
         self.right_context = max(right_context, 0)
@@ -1449,6 +1451,7 @@
             self._ctx = self.asr_model.encoder.get_encoder_input_size(
                 self.window_size
             )
+            self._right_ctx = right_context
 
             self.last_chunk_length = (
                     self.asr_model.encoder.embed.min_frame_length + self.right_context + 1
@@ -1546,6 +1549,37 @@
         return nbest_hyps
 
     @torch.no_grad()
+    def full_utt_decode(self, speech: Union[torch.Tensor, np.ndarray]) -> List[HypothesisTransducer]:
+        """Speech2Text call.
+        Args:
+            speech: Speech data. (S)
+        Returns:
+            nbest_hypothesis: N-best hypothesis.
+        """
+        assert check_argument_types()
+
+        if isinstance(speech, np.ndarray):
+            speech = torch.tensor(speech)
+
+        if self.frontend is not None:
+            speech = torch.unsqueeze(speech, axis=0)
+            speech_lengths = speech.new_full([1], dtype=torch.long, fill_value=speech.size(1))
+            feats, feats_lengths = self.frontend(speech, speech_lengths)
+        else:
+            feats = speech.unsqueeze(0).to(getattr(torch, self.dtype))
+            feats_lengths = feats.new_full([1], dtype=torch.long, fill_value=feats.size(1))
+
+        if self.asr_model.normalize is not None:
+            feats, feats_lengths = self.asr_model.normalize(feats, feats_lengths)
+
+        feats = to_device(feats, device=self.device)
+        feats_lengths = to_device(feats_lengths, device=self.device)
+        enc_out = self.asr_model.encoder.full_utt_forward(feats, feats_lengths)
+        nbest_hyps = self.beam_search(enc_out[0])
+
+        return nbest_hyps
+
+    @torch.no_grad()
     def __call__(self, speech: Union[torch.Tensor, np.ndarray]) -> List[HypothesisTransducer]:
         """Speech2Text call.
         Args:
diff --git a/funasr/bin/asr_inference_launch.py b/funasr/bin/asr_inference_launch.py
index 0fd5abd..a0f21da 100644
--- a/funasr/bin/asr_inference_launch.py
+++ b/funasr/bin/asr_inference_launch.py
@@ -1290,6 +1290,7 @@
         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 +1367,7 @@
         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 +1418,7 @@
                         _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 +1426,8 @@
                     )
                 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)
 

--
Gitblit v1.9.1