Initial commit: FunASR Speech Recognition Toolkit

Add complete FunASR codebase including models, runtime, and documentation.

fun_text_processing/text_normalization/de/verbalizers/cardinal.py

@@ -0,0 +1,28 @@
+import pynini
+from fun_text_processing.text_normalization.en.graph_utils import DAMO_NOT_QUOTE, GraphFst
+from pynini.lib import pynutil
+
+
+class CardinalFst(GraphFst):
+    """
+    Finite state transducer for verbalizing cardinals
+        e.g. cardinal { integer: "zwei" } -> "zwei"
+
+    Args:
+        deterministic: if True will provide a single transduction option,
+            for False multiple transduction are generated (used for audio-based normalization)
+    """
+
+    def __init__(self, deterministic: bool = True):
+        super().__init__(name="cardinal", kind="verbalize", deterministic=deterministic)
+        optional_sign = pynini.closure(pynini.cross('negative: "true" ', "minus "), 0, 1)
+        self.optional_sign = optional_sign
+        integer = pynini.closure(DAMO_NOT_QUOTE, 1)
+
+        self.integer = pynutil.delete(' "') + integer + pynutil.delete('"')
+
+        integer = pynutil.delete("integer:") + self.integer
+        self.numbers = integer
+        graph = optional_sign + self.numbers
+        delete_tokens = self.delete_tokens(graph)
+        self.fst = delete_tokens.optimize()