add a test checking the format of convert_tokens_to_string's output

tests/byt5/test_tokenization_byt5.py

@@ -321,3 +321,12 @@ def test_pretokenized_inputs(self):
     # tests all ids in vocab => vocab doesn't exist so unnecessary to test
     def test_conversion_reversible(self):
         pass
+
+    def test_convert_tokens_to_string_format(self):
+        tokenizers = self.get_tokenizers(fast=True, do_lower_case=True)
+        for tokenizer in tokenizers:
+            with self.subTest(f"{tokenizer.__class__.__name__}"):
+                tokens = ["t", "h", "i", "s", " ", "i", "s", " ", "a", " ", "t", "e", "x", "t", "</s>"]
+                string = tokenizer.convert_tokens_to_string(tokens)
+
+                self.assertIsInstance(string, str)

tests/perceiver/test_tokenization_perceiver.py

@@ -286,3 +286,12 @@ def test_pretokenized_inputs(self):
     # tests all ids in vocab => vocab doesn't exist so unnecessary to test
     def test_conversion_reversible(self):
         pass
+
+    def test_convert_tokens_to_string_format(self):
+        tokenizers = self.get_tokenizers(fast=True, do_lower_case=True)
+        for tokenizer in tokenizers:
+            with self.subTest(f"{tokenizer.__class__.__name__}"):
+                tokens = ["[CLS]", "t", "h", "i", "s", " ", "i", "s", " ", "a", " ", "t", "e", "s", "t", "[SEP]"]
+                string = tokenizer.convert_tokens_to_string(tokens)
+
+                self.assertIsInstance(string, str)

tests/test_tokenization_common.py

@@ -3713,6 +3713,15 @@ def test_saving_tokenizer_trainer(self):
                     trainer.save_model(os.path.join(tmp_dir, "checkpoint"))
                     self.assertIn("tokenizer.json", os.listdir(os.path.join(tmp_dir, "checkpoint")))
 
+    def test_convert_tokens_to_string_format(self):
+        tokenizers = self.get_tokenizers(fast=True, do_lower_case=True)
+        for tokenizer in tokenizers:
+            with self.subTest(f"{tokenizer.__class__.__name__}"):
+                tokens = ["this", "is", "a", "test"]
+                string = tokenizer.convert_tokens_to_string(tokens)
+
+                self.assertIsInstance(string, str)
+
     def test_save_slow_from_fast_and_reload_fast(self):
         if not self.test_slow_tokenizer or not self.test_rust_tokenizer:
             # we need both slow and fast versions

tests/wav2vec2/test_tokenization_wav2vec2.py

@@ -753,3 +753,12 @@ def test_tf_encode_plus_sent_to_model(self):
     @unittest.skip("The tokenizer shouldn't be used to encode input IDs (except for labels), only to decode.")
     def test_torch_encode_plus_sent_to_model(self):
         pass
+
+    def test_convert_tokens_to_string_format(self):
+        tokenizers = self.get_tokenizers(fast=True, do_lower_case=True)
+        for tokenizer in tokenizers:
+            with self.subTest(f"{tokenizer.__class__.__name__}"):
+                tokens = ["T", "H", "I", "S", "|", "I", "S", "|", "A", "|", "T", "E", "X", "T"]
+                output = tokenizer.convert_tokens_to_string(tokens)
+
+                self.assertIsInstance(output["text"], str)

tests/wav2vec2_phoneme/test_tokenization_wav2vec2_phoneme.py

@@ -398,3 +398,12 @@ def test_tf_encode_plus_sent_to_model(self):
     @unittest.skip("The tokenizer shouldn't be used to encode input IDs (except for labels), only to decode.")
     def test_torch_encode_plus_sent_to_model(self):
         pass
+
+    def test_convert_tokens_to_string_format(self):
+        tokenizers = self.get_tokenizers(fast=True, do_lower_case=True)
+        for tokenizer in tokenizers:
+            with self.subTest(f"{tokenizer.__class__.__name__}"):
+                tokens = ["ð", "ɪ", "s", "ɪ", "z", "ɐ", "t", "ɛ", "k", "s", "t"]
+                output = tokenizer.convert_tokens_to_string(tokens)
+
+                self.assertIsInstance(output["text"], str)