forked from mozilla/DeepSpeech
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathdeepspeech.cc
More file actions
319 lines (271 loc) · 9.75 KB
/
Copy pathdeepspeech.cc
File metadata and controls
319 lines (271 loc) · 9.75 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
#ifdef DS_NATIVE_MODEL
#define EIGEN_USE_THREADS
#define EIGEN_USE_CUSTOM_THREAD_POOL
#include "third_party/eigen3/unsupported/Eigen/CXX11/Tensor"
#include "native_client/deepspeech_model.h" // generated
#endif
#include <iostream>
#include "deepspeech.h"
#include "deepspeech_utils.h"
#include "alphabet.h"
#include "beam_search.h"
#include "tensorflow/core/public/session.h"
#include "tensorflow/core/platform/env.h"
#define BATCH_SIZE 1
using namespace tensorflow;
using tensorflow::ctc::CTCBeamSearchDecoder;
using tensorflow::ctc::CTCDecoder;
namespace DeepSpeech {
class Private {
public:
Session* session;
GraphDef graph_def;
int ncep;
int ncontext;
Alphabet* alphabet;
KenLMBeamScorer* scorer;
int beam_width;
bool run_aot;
};
Model::Model(const char* aModelPath, int aNCep, int aNContext,
const char* aAlphabetConfigPath, int aBeamWidth)
{
mPriv = new Private;
mPriv->session = NULL;
mPriv->scorer = NULL;
mPriv->ncep = aNCep;
mPriv->ncontext = aNContext;
mPriv->alphabet = new Alphabet(aAlphabetConfigPath);
mPriv->beam_width = aBeamWidth;
mPriv->run_aot = false;
if (!aModelPath || strlen(aModelPath) < 1) {
std::cerr << "No model specified, will rely on built-in model." << std::endl;
mPriv->run_aot = true;
return;
}
Status status = NewSession(SessionOptions(), &mPriv->session);
if (!status.ok()) {
std::cerr << status.ToString() << std::endl;
return;
}
status = ReadBinaryProto(Env::Default(), aModelPath, &mPriv->graph_def);
if (!status.ok()) {
mPriv->session->Close();
mPriv->session = NULL;
std::cerr << status.ToString() << std::endl;
return;
}
status = mPriv->session->Create(mPriv->graph_def);
if (!status.ok()) {
mPriv->session->Close();
mPriv->session = NULL;
std::cerr << status.ToString() << std::endl;
return;
}
for (int i = 0; i < mPriv->graph_def.node_size(); ++i) {
NodeDef node = mPriv->graph_def.node(i);
if (node.name() == "logits/shape/2") {
int final_dim_size = node.attr().at("value").tensor().int_val(0) - 1;
if (final_dim_size != mPriv->alphabet->GetSize()) {
std::cerr << "Error: Alphabet size does not match loaded model: alphabet "
<< "has size " << mPriv->alphabet->GetSize()
<< ", but model has " << final_dim_size
<< " classes in its output. Make sure you're passing an alphabet "
<< "file with the same size as the one used for training."
<< std::endl;
mPriv->session->Close();
mPriv->session = NULL;
return;
}
break;
}
}
}
Model::~Model()
{
if (mPriv->session) {
mPriv->session->Close();
}
delete mPriv->alphabet;
delete mPriv->scorer;
delete mPriv;
}
void
Model::enableDecoderWithLM(const char* aAlphabetConfigPath, const char* aLMPath,
const char* aTriePath, float aLMWeight,
float aWordCountWeight, float aValidWordCountWeight)
{
mPriv->scorer = new KenLMBeamScorer(aLMPath, aTriePath, aAlphabetConfigPath,
aLMWeight, aWordCountWeight, aValidWordCountWeight);
}
void
Model::getInputVector(const short* aBuffer, unsigned int aBufferSize,
int aSampleRate, float** aMfcc, int* aNFrames,
int* aFrameLen)
{
return audioToInputVector(aBuffer, aBufferSize, aSampleRate, mPriv->ncep,
mPriv->ncontext, aMfcc, aNFrames, aFrameLen);
}
char*
Model::decode(int aNFrames, float*** aLogits)
{
const int batch_size = BATCH_SIZE;
const int top_paths = 1;
const int timesteps = aNFrames;
const size_t num_classes = mPriv->alphabet->GetSize() + 1; // +1 for blank
// Raw data containers (arrays of floats, ints, etc.).
int sequence_lengths[batch_size] = {timesteps};
// Convert data containers to the format accepted by the decoder, simply
// mapping the memory from the container to an Eigen::ArrayXi,::MatrixXf,
// using Eigen::Map.
Eigen::Map<const Eigen::ArrayXi> seq_len(&sequence_lengths[0], batch_size);
std::vector<Eigen::Map<const Eigen::MatrixXf>> inputs;
inputs.reserve(timesteps);
for (int t = 0; t < timesteps; ++t) {
inputs.emplace_back(&aLogits[t][0][0], batch_size, num_classes);
}
// Prepare containers for output and scores.
// CTCDecoder::Output is std::vector<std::vector<int>>
std::vector<CTCDecoder::Output> decoder_outputs(top_paths);
for (CTCDecoder::Output& output : decoder_outputs) {
output.resize(batch_size);
}
float score[batch_size][top_paths] = {{0.0}};
Eigen::Map<Eigen::MatrixXf> scores(&score[0][0], batch_size, top_paths);
if (mPriv->scorer == NULL) {
CTCBeamSearchDecoder<>::DefaultBeamScorer scorer;
CTCBeamSearchDecoder<> decoder(num_classes,
mPriv->beam_width,
&scorer,
batch_size);
decoder.Decode(seq_len, inputs, &decoder_outputs, &scores).ok();
} else {
CTCBeamSearchDecoder<KenLMBeamState> decoder(num_classes,
mPriv->beam_width,
mPriv->scorer,
batch_size);
decoder.Decode(seq_len, inputs, &decoder_outputs, &scores).ok();
}
// Output is an array of shape (1, n_results, result_length).
// In this case, n_results is also equal to 1.
size_t output_length = decoder_outputs[0][0].size() + 1;
size_t decoded_length = 1; // add 1 for the \0
for (int i = 0; i < output_length - 1; i++) {
int64 character = decoder_outputs[0][0][i];
const std::string& str = mPriv->alphabet->StringFromLabel(character);
decoded_length += str.size();
}
char* output = (char*)malloc(sizeof(char) * decoded_length);
char* pen = output;
for (int i = 0; i < output_length - 1; i++) {
int64 character = decoder_outputs[0][0][i];
const std::string& str = mPriv->alphabet->StringFromLabel(character);
strncpy(pen, str.c_str(), str.size());
pen += str.size();
}
*pen = '\0';
for (int i = 0; i < timesteps; ++i) {
for (int j = 0; j < batch_size; ++j) {
free(aLogits[i][j]);
}
free(aLogits[i]);
}
free(aLogits);
return output;
}
char*
Model::infer(float* aMfcc, int aNFrames, int aFrameLen)
{
const int batch_size = BATCH_SIZE;
const int timesteps = aNFrames;
const size_t num_classes = mPriv->alphabet->GetSize() + 1; // +1 for blank
const int frameSize = mPriv->ncep + (2 * mPriv->ncep * mPriv->ncontext);
float*** input_data_mat = (float***)calloc(timesteps, sizeof(float**));
for (int i = 0; i < timesteps; ++i) {
input_data_mat[i] = (float**)calloc(batch_size, sizeof(float*));
for (int j = 0; j < batch_size; ++j) {
input_data_mat[i][j] = (float*)calloc(num_classes, sizeof(float));
}
}
if (mPriv->run_aot) {
#ifdef DS_NATIVE_MODEL
Eigen::ThreadPool tp(2); // Size the thread pool as appropriate.
Eigen::ThreadPoolDevice device(&tp, tp.NumThreads());
nativeModel nm(nativeModel::AllocMode::RESULTS_AND_TEMPS_ONLY);
nm.set_thread_pool(&device);
for (int ot = 0; ot < timesteps; ot += DS_MODEL_TIMESTEPS) {
nm.set_arg0_data(&(aMfcc[ot * frameSize]));
nm.Run();
// The CTCDecoder works with log-probs.
for (int t = 0; t < DS_MODEL_TIMESTEPS, (ot + t) < timesteps; ++t) {
for (int b = 0; b < batch_size; ++b) {
for (int c = 0; c < num_classes; ++c) {
input_data_mat[ot + t][b][c] = nm.result0(t, b, c);
}
}
}
}
#else
std::cerr << "No support for native model built-in." << std::endl;
return NULL;
#endif // DS_NATIVE_MODEL
} else {
if (aFrameLen == 0) {
aFrameLen = frameSize;
} else if (aFrameLen < frameSize) {
std::cerr << "mfcc features array is too small (expected " <<
frameSize << ", got " << aFrameLen << ")\n";
return NULL;
}
Tensor input(DT_FLOAT, TensorShape({1, aNFrames, frameSize}));
auto input_mapped = input.tensor<float, 3>();
for (int i = 0, idx = 0; i < aNFrames; i++) {
for (int j = 0; j < frameSize; j++, idx++) {
input_mapped(0, i, j) = aMfcc[idx];
}
idx += (aFrameLen - frameSize);
}
Tensor n_frames(DT_INT32, TensorShape({1}));
n_frames.scalar<int>()() = aNFrames;
// The CTC Beam Search decoder takes logits as input, we can feed those from
// the "logits" node in official models or
// the "logits_output_node" in old AOT hacking models
std::vector<Tensor> outputs;
Status status = mPriv->session->Run(
{{ "input_node", input }, { "input_lengths", n_frames }},
{"logits"}, {}, &outputs);
// If "logits" doesn't exist, this is an older graph. Try to recover.
if (status.code() == tensorflow::error::NOT_FOUND) {
status.IgnoreError();
status = mPriv->session->Run(
{{ "input_node", input }, { "input_lengths", n_frames }},
{"logits_output_node"}, {}, &outputs);
}
if (!status.ok()) {
std::cerr << "Error running session: " << status.ToString() << "\n";
return NULL;
}
auto logits_mapped = outputs[0].tensor<float, 3>();
// The CTCDecoder works with log-probs.
for (int t = 0; t < timesteps; ++t) {
for (int b = 0; b < batch_size; ++b) {
for (int c = 0; c < num_classes; ++c) {
input_data_mat[t][b][c] = logits_mapped(t, b, c);
}
}
}
}
return decode(aNFrames, input_data_mat);
}
char*
Model::stt(const short* aBuffer, unsigned int aBufferSize, int aSampleRate)
{
float* mfcc;
char* string;
int n_frames;
getInputVector(aBuffer, aBufferSize, aSampleRate, &mfcc, &n_frames, NULL);
string = infer(mfcc, n_frames);
free(mfcc);
return string;
}
}