From 494cb5c7330bc6dbf87fe62955cea88a14c05ea1 Mon Sep 17 00:00:00 2001
From: Fangjun Kuang <csukuangfj@gmail.com>
Date: Mon, 22 Apr 2024 15:10:39 +0800
Subject: [PATCH] Fix the last character not being recognized for streaming
 paraformer models. (#799)

---
 sherpa-onnx/csrc/sherpa-onnx-alsa.cc       | 14 ++++++++++++++
 sherpa-onnx/csrc/sherpa-onnx-microphone.cc | 13 +++++++++++++
 2 files changed, 27 insertions(+)

diff --git a/sherpa-onnx/csrc/sherpa-onnx-alsa.cc b/sherpa-onnx/csrc/sherpa-onnx-alsa.cc
index a0c4e3d6..689fb19a 100644
--- a/sherpa-onnx/csrc/sherpa-onnx-alsa.cc
+++ b/sherpa-onnx/csrc/sherpa-onnx-alsa.cc
@@ -113,6 +113,20 @@ as the device_name.
 
     bool is_endpoint = recognizer.IsEndpoint(stream.get());
 
+    if (is_endpoint && !config.model_config.paraformer.encoder.empty()) {
+      // For streaming paraformer models, since it has a large right chunk size
+      // we need to pad it on endpointing so that the last character
+      // can be recognized
+      std::vector<float> tail_paddings(
+          static_cast<int>(1.0 * expected_sample_rate));
+      stream->AcceptWaveform(expected_sample_rate, tail_paddings.data(),
+                             tail_paddings.size());
+      while (recognizer.IsReady(stream.get())) {
+        recognizer.DecodeStream(stream.get());
+      }
+      text = recognizer.GetResult(stream.get()).text;
+    }
+
     if (!text.empty() && last_text != text) {
       last_text = text;
 
diff --git a/sherpa-onnx/csrc/sherpa-onnx-microphone.cc b/sherpa-onnx/csrc/sherpa-onnx-microphone.cc
index 1b6760b5..0e32625e 100644
--- a/sherpa-onnx/csrc/sherpa-onnx-microphone.cc
+++ b/sherpa-onnx/csrc/sherpa-onnx-microphone.cc
@@ -157,6 +157,19 @@ for a list of pre-trained models to download.
     auto text = recognizer.GetResult(s.get()).text;
     bool is_endpoint = recognizer.IsEndpoint(s.get());
 
+    if (is_endpoint && !config.model_config.paraformer.encoder.empty()) {
+      // For streaming paraformer models, since it has a large right chunk size
+      // we need to pad it on endpointing so that the last character
+      // can be recognized
+      std::vector<float> tail_paddings(static_cast<int>(1.0 * mic_sample_rate));
+      s->AcceptWaveform(mic_sample_rate, tail_paddings.data(),
+                        tail_paddings.size());
+      while (recognizer.IsReady(s.get())) {
+        recognizer.DecodeStream(s.get());
+      }
+      text = recognizer.GetResult(s.get()).text;
+    }
+
     if (!text.empty() && last_text != text) {
       last_text = text;