Add C and CXX API for Dolphin CTC models (#2088)

2025-04-02 21:54:20 +08:00
parent eee5575836
commit da4aad1189
12 changed files with 231 additions and 5 deletions
--- a/c-api-examples/dolphin-ctc-c-api.c
+++ b/c-api-examples/dolphin-ctc-c-api.c
@@ -0,0 +1,74 @@
+// c-api-examples/dolphin-ctc-c-api.c
+//
+// Copyright (c)  2025  Xiaomi Corporation
+
+//
+// This file demonstrates how to use Dolphin CTC model with sherpa-onnx's C API.
+// clang-format off
+//
+// wget https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-dolphin-base-ctc-multi-lang-int8-2025-04-02
+// tar xvf sherpa-onnx-dolphin-base-ctc-multi-lang-int8-2025-04-02.tar.bz2
+// rm sherpa-onnx-dolphin-base-ctc-multi-lang-int8-2025-04-02.tar.bz2
+//
+// clang-format on
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "sherpa-onnx/c-api/c-api.h"
+
+int32_t main() {
+  // clang-format off
+  const char *wav_filename = "./sherpa-onnx-dolphin-base-ctc-multi-lang-int8-2025-04-02/test_wavs/0.wav";
+  const char *model_filename = "./sherpa-onnx-dolphin-base-ctc-multi-lang-int8-2025-04-02/model.int8.onnx";
+  const char *tokens_filename = "./sherpa-onnx-dolphin-base-ctc-multi-lang-int8-2025-04-02/tokens.txt";
+  // clang-format on
+
+  const SherpaOnnxWave *wave = SherpaOnnxReadWave(wav_filename);
+  if (wave == NULL) {
+    fprintf(stderr, "Failed to read %s\n", wav_filename);
+    return -1;
+  }
+
+  SherpaOnnxOfflineModelConfig offline_model_config;
+  memset(&offline_model_config, 0, sizeof(offline_model_config));
+  offline_model_config.debug = 1;
+  offline_model_config.num_threads = 1;
+  offline_model_config.provider = "cpu";
+  offline_model_config.tokens = tokens_filename;
+  offline_model_config.dolphin.model = model_filename;
+
+  // Recognizer config
+  SherpaOnnxOfflineRecognizerConfig recognizer_config;
+  memset(&recognizer_config, 0, sizeof(recognizer_config));
+  recognizer_config.decoding_method = "greedy_search";
+  recognizer_config.model_config = offline_model_config;
+
+  const SherpaOnnxOfflineRecognizer *recognizer =
+      SherpaOnnxCreateOfflineRecognizer(&recognizer_config);
+
+  if (recognizer == NULL) {
+    fprintf(stderr, "Please check your config!\n");
+    SherpaOnnxFreeWave(wave);
+    return -1;
+  }
+
+  const SherpaOnnxOfflineStream *stream =
+      SherpaOnnxCreateOfflineStream(recognizer);
+
+  SherpaOnnxAcceptWaveformOffline(stream, wave->sample_rate, wave->samples,
+                                  wave->num_samples);
+  SherpaOnnxDecodeOfflineStream(recognizer, stream);
+  const SherpaOnnxOfflineRecognizerResult *result =
+      SherpaOnnxGetOfflineStreamResult(stream);
+
+  fprintf(stderr, "Decoded text: %s\n", result->text);
+
+  SherpaOnnxDestroyOfflineRecognizerResult(result);
+  SherpaOnnxDestroyOfflineStream(stream);
+  SherpaOnnxDestroyOfflineRecognizer(recognizer);
+  SherpaOnnxFreeWave(wave);
+
+  return 0;
+}