support offline inference for unified streaming/non-streaming rnnt

aky15

2023-08-14 a5cd4bb473b19fe2af1753fa7e60a997a8208447

 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)