add new language test

test that the pipeline can return both the language and timestamp

tests/pipelines/test_pipelines_automatic_speech_recognition.py

@@ -324,7 +324,6 @@ def test_torch_large_with_input_features(self):
 
     @slow
     @require_torch
-    @slow
     def test_return_timestamps_in_preprocess(self):
         pipe = pipeline(
             task="automatic-speech-recognition",
@@ -368,6 +367,63 @@ def test_return_timestamps_in_preprocess(self):
         )
         # fmt: on
 
+    @slow
+    @require_torch
+    def test_return_timestamps_and_language_in_preprocess(self):
+        pipe = pipeline(
+            task="automatic-speech-recognition",
+            model="openai/whisper-tiny",
+            chunk_length_s=8,
+            stride_length_s=1,
+            return_language=True,
+        )
+        data = load_dataset("openslr/librispeech_asr", "clean", split="test", streaming=True, trust_remote_code=True)
+        sample = next(iter(data))
+        pipe.model.config.forced_decoder_ids = pipe.tokenizer.get_decoder_prompt_ids(language="en", task="transcribe")
+
+        res = pipe(sample["audio"]["array"])
+        self.assertEqual(
+            res,
+            {
+                "text": " Conquered returned to its place amidst the tents.",
+                "chunks": [{"language": "english", "text": " Conquered returned to its place amidst the tents."}],
+            },
+        )
+        res = pipe(sample["audio"]["array"], return_timestamps=True)
+        self.assertEqual(
+            res,
+            {
+                "text": " Conquered returned to its place amidst the tents.",
+                "chunks": [
+                    {
+                        "timestamp": (0.0, 3.36),
+                        "language": "english",
+                        "text": " Conquered returned to its place amidst the tents.",
+                    }
+                ],
+            },
+        )
+        pipe.model.generation_config.alignment_heads = [[2, 2], [3, 0], [3, 2], [3, 3], [3, 4], [3, 5]]
+        res = pipe(sample["audio"]["array"], return_timestamps="word")
+        # fmt: off
+        self.assertEqual(
+            res,
+            {
+                'text': ' Conquered returned to its place amidst the tents.',
+                'chunks': [
+                    {"language": "english",'text': ' Conquered', 'timestamp': (0.5, 1.2)},
+                    {"language": "english", 'text': ' returned', 'timestamp': (1.2, 1.64)},
+                    {"language": "english",'text': ' to', 'timestamp': (1.64, 1.84)},
+                    {"language": "english",'text': ' its', 'timestamp': (1.84, 2.02)},
+                    {"language": "english",'text': ' place', 'timestamp': (2.02, 2.28)},
+                    {"language": "english",'text': ' amidst', 'timestamp': (2.28, 2.8)},
+                    {"language": "english",'text': ' the', 'timestamp': (2.8, 2.98)},
+                    {"language": "english",'text': ' tents.', 'timestamp': (2.98, 3.48)},
+                ],
+            },
+        )
+        # fmt: on
+
     @slow
     @require_torch
     def test_return_timestamps_in_preprocess_longform(self):