Merge pull request #792 from kuke/expose_acoustic_scale

Expose acoustic scale in decoder
PaddlePaddle · Mar 29, 2018 · 05f36d8 · 05f36d8
2 parents bf38065 + 4a8e399
commit 05f36d8
Show file tree

Hide file tree

Showing 5 changed files with 18 additions and 4 deletions.
diff --git a/fluid/DeepASR/data_utils/util.py b/fluid/DeepASR/data_utils/util.py
@@ -35,6 +35,13 @@ def lodtensor_to_ndarray(lod_tensor):
     return ret, lod_tensor.lod()
 
 
+def split_infer_result(infer_seq, lod):
+    infer_batch = []
+    for i in xrange(0, len(lod[0]) - 1):
+        infer_batch.append(infer_seq[lod[0][i]:lod[0][i + 1]])
+    return infer_batch
+
+
 class CriticalException(Exception):
     pass
 

diff --git a/fluid/DeepASR/decoder/post_decode_faster.cc b/fluid/DeepASR/decoder/post_decode_faster.cc
@@ -21,14 +21,15 @@ using fst::StdArc;
 
 Decoder::Decoder(std::string word_syms_filename,
                  std::string fst_in_filename,
-                 std::string logprior_rxfilename) {
+                 std::string logprior_rxfilename,
+                 kaldi::BaseFloat acoustic_scale) {
   const char* usage =
       "Decode, reading log-likelihoods (of transition-ids or whatever symbol "
       "is on the graph) as matrices.";
 
   kaldi::ParseOptions po(usage);
   binary = true;
-  acoustic_scale = 1.5;
+  this->acoustic_scale = acoustic_scale;
   allow_partial = true;
   kaldi::FasterDecoderOptions decoder_opts;
   decoder_opts.Register(&po, true);  // true == include obscure settings.

diff --git a/fluid/DeepASR/decoder/post_decode_faster.h b/fluid/DeepASR/decoder/post_decode_faster.h
@@ -29,7 +29,8 @@ class Decoder {
 public:
   Decoder(std::string word_syms_filename,
           std::string fst_in_filename,
-          std::string logprior_rxfilename);
+          std::string logprior_rxfilename,
+          kaldi::BaseFloat acoustic_scale);
   ~Decoder();
 
   // Interface to accept the scores read from specifier and return

diff --git a/fluid/DeepASR/decoder/pybind.cc b/fluid/DeepASR/decoder/pybind.cc
@@ -23,7 +23,7 @@ PYBIND11_MODULE(post_decode_faster, m) {
   m.doc() = "Decoder for Deep ASR model";
 
   py::class_<Decoder>(m, "Decoder")
-      .def(py::init<std::string, std::string, std::string>())
+      .def(py::init<std::string, std::string, std::string, kaldi::BaseFloat>())
       .def("decode",
            (std::vector<std::string> (Decoder::*)(std::string)) &
                Decoder::decode,

diff --git a/fluid/DeepASR/infer_by_ckpt.py b/fluid/DeepASR/infer_by_ckpt.py
@@ -106,6 +106,11 @@ def parse_args():
         type=str,
         default="./decoder/logprior",
         help="The log prior probs for training data. (default: %(default)s)")
+    parser.add_argument(
+        '--acoustic_scale',
+        type=float,
+        default=0.2,
+        help="Scaling factor for acoustic likelihoods. (default: %(default)f)")
     args = parser.parse_args()
     return args