Initial commit: FunASR Speech Recognition Toolkit

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

funasr/tokenizer/word_tokenizer.py

@@ -0,0 +1,73 @@
+from pathlib import Path
+from typing import Iterable
+from typing import List
+from typing import Union
+import warnings
+
+
+from funasr.tokenizer.abs_tokenizer import AbsTokenizer
+
+
+class WordTokenizer(AbsTokenizer):
+    def __init__(
+        self,
+        delimiter: str = None,
+        non_linguistic_symbols: Union[Path, str, Iterable[str]] = None,
+        remove_non_linguistic_symbols: bool = False,
+    ):
+        """Initialize WordTokenizer.
+        
+            Args:
+                delimiter: TODO.
+                non_linguistic_symbols: TODO.
+                remove_non_linguistic_symbols: TODO.
+            """
+        self.delimiter = delimiter
+
+        if not remove_non_linguistic_symbols and non_linguistic_symbols is not None:
+            warnings.warn(
+                "non_linguistic_symbols is only used " "when remove_non_linguistic_symbols = True"
+            )
+
+        if non_linguistic_symbols is None:
+            self.non_linguistic_symbols = set()
+        elif isinstance(non_linguistic_symbols, (Path, str)):
+            non_linguistic_symbols = Path(non_linguistic_symbols)
+            try:
+                with non_linguistic_symbols.open("r", encoding="utf-8") as f:
+                    self.non_linguistic_symbols = set(line.rstrip() for line in f)
+            except FileNotFoundError:
+                warnings.warn(f"{non_linguistic_symbols} doesn't exist.")
+                self.non_linguistic_symbols = set()
+        else:
+            self.non_linguistic_symbols = set(non_linguistic_symbols)
+        self.remove_non_linguistic_symbols = remove_non_linguistic_symbols
+
+    def __repr__(self):
+        """Internal: repr  ."""
+        return f'{self.__class__.__name__}(delimiter="{self.delimiter}")'
+
+    def text2tokens(self, line: str) -> List[str]:
+        """Text2tokens.
+        
+            Args:
+                line: TODO.
+            """
+        tokens = []
+        for t in line.split(self.delimiter):
+            if self.remove_non_linguistic_symbols and t in self.non_linguistic_symbols:
+                continue
+            tokens.append(t)
+        return tokens
+
+    def tokens2text(self, tokens: Iterable[str]) -> str:
+        """Tokens2text.
+        
+            Args:
+                tokens: TODO.
+            """
+        if self.delimiter is None:
+            delimiter = " "
+        else:
+            delimiter = self.delimiter
+        return delimiter.join(tokens)