OVModelForSpeechSeq2Seq fails with return_timestamps="word".

@helena-intel

This works:
```python
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq, GenerationConfig, pipeline
from pathlib import Path
from optimum.intel.openvino import OVModelForSpeechSeq2Seq
import openvino as ov
import json

model_id = "openai/whisper-small"
model = AutoModelForSpeechSeq2Seq.from_pretrained(model_id)
processor = AutoProcessor.from_pretrained(model_id)
generation_config = GenerationConfig.from_pretrained(model_id)

ov_config = {"CACHE_DIR": ""}
model_path = Path(model_id.replace('/', '_'))

if not model_path.exists():
ov_model = OVModelForSpeechSeq2Seq.from_pretrained(
model_id, ov_config=ov_config, export=True, compile=False, load_in_8bit=False
)
ov_model.half()
ov_model.save_pretrained(model_path)
else:
ov_model = OVModelForSpeechSeq2Seq.from_pretrained(
model_path, ov_config=ov_config, compile=False
)

ov_model.generation_config = generation_config

device = 'gpu'
ov_model.to(device)
ov_model.compile()

pipe = pipeline(
"automatic-speech-recognition",
model=ov_model,
tokenizer=processor.tokenizer,
feature_extractor=processor.feature_extractor,
chunk_length_s=30,
batch_size=18,
)
result = pipe("./4.wav")

with open("sample.json", "w") as outfile:
json.dump(result, outfile)
print(result["text"])
```

This doesn't (added ``return_timestamps="word"`` at line 40):
```python
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq, GenerationConfig, pipeline
from pathlib import Path
from optimum.intel.openvino import OVModelForSpeechSeq2Seq
import openvino as ov
import json

model_id = "openai/whisper-small"
model = AutoModelForSpeechSeq2Seq.from_pretrained(model_id)
processor = AutoProcessor.from_pretrained(model_id)
generation_config = GenerationConfig.from_pretrained(model_id)

ov_config = {"CACHE_DIR": ""}
model_path = Path(model_id.replace('/', '_'))

if not model_path.exists():
ov_model = OVModelForSpeechSeq2Seq.from_pretrained(
model_id, ov_config=ov_config, export=True, compile=False, load_in_8bit=False
)
ov_model.half()
ov_model.save_pretrained(model_path)
else:
ov_model = OVModelForSpeechSeq2Seq.from_pretrained(
model_path, ov_config=ov_config, compile=False
)

ov_model.generation_config = generation_config

device = 'gpu'
ov_model.to(device)
ov_model.compile()

pipe = pipeline(
"automatic-speech-recognition",
model=ov_model,
tokenizer=processor.tokenizer,
feature_extractor=processor.feature_extractor,
chunk_length_s=30,
batch_size=18,
)
result = pipe("./4.wav", return_timestamps="word")
with open("sample.json", "w") as outfile:
json.dump(result, outfile)
print(result["text"])
```

and fails with:
```python
INFO:nncf:NNCF initialized successfully. Supported frameworks detected: torch, onnx, openvino
Compiling the encoder to GPU ...
Compiling the decoder to GPU ...
Compiling the decoder to GPU ...
device must be of type but got instead
Traceback (most recent call last):
File "/run/media/greggy/1a4fd6d7-1f9d-42c6-9324-661804695013/D/owisp/./n2.py", line 44, in
result = pipe("./4.wav", return_timestamps="word")
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/greggy/.local/lib/python3.11/site-packages/transformers/pipelines/automatic_speech_recognition.py", line 292, in __call__
return super().__call__(inputs, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/greggy/.local/lib/python3.11/site-packages/transformers/pipelines/base.py", line 1154, in __call__
return next(
^^^^^
File "/home/greggy/.local/lib/python3.11/site-packages/transformers/pipelines/pt_utils.py", line 124, in __next__
item = next(self.iterator)
^^^^^^^^^^^^^^^^^^^
File "/home/greggy/.local/lib/python3.11/site-packages/transformers/pipelines/pt_utils.py", line 266, in __next__
processed = self.infer(next(self.iterator), **self.params)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/greggy/.local/lib/python3.11/site-packages/transformers/pipelines/base.py", line 1068, in forward
model_outputs = self._forward(model_inputs, **forward_params)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/greggy/.local/lib/python3.11/site-packages/transformers/pipelines/automatic_speech_recognition.py", line 507, in _forward
tokens = self.model.generate(
^^^^^^^^^^^^^^^^^^^^
File "/home/greggy/.local/lib/python3.11/site-packages/optimum/intel/openvino/modeling_seq2seq.py", line 1018, in generate
outputs["token_timestamps"] = self._extract_token_timestamps(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
AttributeError: '_OVModelForWhisper' object has no attribute '_extract_token_timestamps'
```
Of course non-OpenVino, purely transformers script works too and returns word level timestamps successfully.