Fix bug in lexicon compiler (#16)

docs/source/conf.py

@@ -173,8 +173,7 @@
 # autodoc_typehints_description_target = 'documented'
 # autoclass_content = 'both'
 autodoc_docstring_signature = True
-autodoc_type_aliases = {
-}
+autodoc_type_aliases = {}
 
 napoleon_preprocess_types = False
 napoleon_attr_annotations = False
@@ -245,7 +244,7 @@
 # The reST default role (used for this markup: `text`) to use for all
 # documents.
 #
-default_role = "autolink"
+default_role = "code"
 
 # If true, '()' will be appended to :func: etc. cross-reference text.
 #
@@ -262,9 +261,7 @@
 # show_authors = False
 
 # nitpicky = True
-nitpick_ignore = [
-
-]
+nitpick_ignore = []
 
 # The name of the Pygments (syntax highlighting) style to use.
 pygments_style = "sphinx"
@@ -512,9 +509,7 @@
 # Grouping the document tree into Texinfo files. List of tuples
 # (source start file, target name, title, author,
 #  dir menu entry, description, category)
-texinfo_documents = [
-
-]
+texinfo_documents = []
 
 # Documents to append as an appendix to all manuals.
 #

environment.yml

@@ -10,7 +10,7 @@ dependencies:
   - kaldi=*=*cpu*
   - scipy
   - pynini
-  - openfst
+  - openfst=1.8.3
   - setuptools_scm
   - pybind11
   - pytest

extensions/feat/feat.cpp

@@ -209,6 +209,7 @@ void feat_feat_functions(py::module& m){
                    left_context,
                    right_context,
                             &output_features);
+              py::gil_scoped_acquire acquire;
             return output_features;
 
         },

kalpy/feat/mfcc.py

@@ -82,7 +82,7 @@ def __init__(
         sample_frequency: float = 16000,
         frame_length: int = 25,
         frame_shift: int = 10,
-        dither: float = 1.0,
+        dither: float = 0.0,
         preemphasis_coefficient: float = 0.97,
         remove_dc_offset: bool = True,
         window_type: str = "povey",
@@ -97,7 +97,7 @@ def __init__(
         vtln_high: float = -500,
         num_coefficients: int = 13,
         use_energy: bool = True,
-        energy_floor: float = 0.0,
+        energy_floor: float = 1.0,
         raw_energy: bool = True,
         cepstral_lifter: float = 22.0,
         htk_compatibility: bool = False,

kalpy/fstext/lexicon.py

@@ -26,11 +26,11 @@ class Pronunciation:
 
     orthography: str
     pronunciation: str
-    probability: typing.Optional[float]
-    silence_after_probability: typing.Optional[float]
-    silence_before_correction: typing.Optional[float]
-    non_silence_before_correction: typing.Optional[float]
-    disambiguation: typing.Optional[int]
+    probability: typing.Optional[float] = None
+    silence_after_probability: typing.Optional[float] = None
+    silence_before_correction: typing.Optional[float] = None
+    non_silence_before_correction: typing.Optional[float] = None
+    disambiguation: typing.Optional[int] = None
 
 
 def parse_dictionary_file(
@@ -192,10 +192,9 @@ def __init__(
         self._align_lexicon = None
         self.word_begin_label = word_begin_label
         self.word_end_label = word_end_label
-        self.start_state = None
-        self.loop_state = None
-        self.silence_state = None
-        self.non_silence_state = None
+        self.start_state = 0
+        self.non_silence_state = 1
+        self.silence_state = 2
 
     def clear(self):
         self.pronunciations = []
@@ -364,12 +363,17 @@ def create_fsts(self, phonological_rule_fst: pynini.Fst = None):
         self.word_table.find(self.silence_word)
         self._fst = pynini.Fst()
         self._align_fst = pynini.Fst()
-        self.start_state = self._fst.add_state()
+        # Start state = 0
+        self._fst.add_state()
         self._align_fst.add_state()
         self._fst.set_start(self.start_state)
-        self.non_silence_state = self._fst.add_state()  # Also loop state
+
+        # Non silence state = 1
+        self._fst.add_state()  # Also loop state
         self._align_fst.add_state()
-        self.silence_state = self._fst.add_state()
+
+        # Silence state = 2
+        self._fst.add_state()
         self._align_fst.add_state()
 
         self._align_fst.set_start(self.start_state)