hybrid_rnnt_ctc_bpe model has no inference code

[aidos-aiforiatech]

Describe the bug

I am training examples/asr/asr_hybrid_transducer_ctc/speech_to_text_hybrid_rnnt_ctc_bpe.py.

I cannot run the inference obtaining the following exception:

Error executing job with overrides: ['model_path=results/UZB_MCV_ISSAI_V2/2024-03-15_16-25-00/checkpoints/UZB_MCV_ISSAI_V2.[8/1287$
pretrained_name=null', 'dataset_manifest=/home/aidos/datasets/tbc_test.json', 'batch_size=32', 'output_filename=results/UZB_MCV_ISS
AI_V2/2024-03-15_16-25-00/tbc_test_pred.json']                                                                                     
Traceback (most recent call last):                                                                                                 
  File "/home/aidos/exp/NeMo/examples/asr/speech_to_text_eval.py", line 225, in <module>                                           
    main()  # noqa pylint: disable=no-value-for-parameter                                                                          
  File "/home/aidos/exp/Nemo_inf/NeMo/nemo/core/config/hydra_runner.py", line 129, in wrapper                                      
    _run_hydra(                                                                                                                    
  File "/home/aidos/nemo_inference_venv/lib/python3.10/site-packages/hydra/_internal/utils.py", line 394, in _run_hydra            
    _run_app(
  File "/home/aidos/nemo_inference_venv/lib/python3.10/site-packages/hydra/_internal/utils.py", line 457, in _run_app
    run_and_report(
  File "/home/aidos/nemo_inference_venv/lib/python3.10/site-packages/hydra/_internal/utils.py", line 223, in run_and_report
    raise ex
  File "/home/aidos/nemo_inference_venv/lib/python3.10/site-packages/hydra/_internal/utils.py", line 220, in run_and_report
    return func()
  File "/home/aidos/nemo_inference_venv/lib/python3.10/site-packages/hydra/_internal/utils.py", line 458, in <lambda>
    lambda: hydra.run(
  File "/home/aidos/nemo_inference_venv/lib/python3.10/site-packages/hydra/_internal/hydra.py", line 132, in run
    _ = ret.return_value
  File "/home/aidos/nemo_inference_venv/lib/python3.10/site-packages/hydra/core/utils.py", line 260, in return_value
    raise self._return_value
  File "/home/aidos/nemo_inference_venv/lib/python3.10/site-packages/hydra/core/utils.py", line 186, in run_job
    ret.return_value = task_function(task_cfg)
  File "/home/aidos/exp/NeMo/examples/asr/speech_to_text_eval.py", line 125, in main
    transcription_cfg = transcribe_speech.main(cfg)  # type: EvaluationConfig
  File "/home/aidos/exp/Nemo_inf/NeMo/nemo/core/config/hydra_runner.py", line 75, in wrapper
    return task_function(cfg_passthrough)
  File "/home/aidos/exp/NeMo/examples/asr/transcribe_speech.py", line 393, in main
    transcriptions = asr_model.transcribe(audio=filepaths, override_config=override_cfg,)
  File "/home/aidos/nemo_inference_venv/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs) 
TypeError: EncDecHybridRNNTCTCModel.transcribe() got an unexpected keyword argument 'override_config'

Steps/Code to reproduce bug

python ${NEMO_ROOT}/examples/asr/speech_to_text_eval.py \
    model_path=${MODEL} \
    pretrained_name=null \
    dataset_manifest=${TEST_MANIFEST} \
    batch_size=${BATCH_SIZE} \
    output_filename=${OUTPUT_MANIFEST} \
    amp=False \
    use_cer=False)

Expected behavior

An inference process

Environment overview (please complete the following information)

• Environment location: GCP
• Method of NeMo install: pip install

Environment details

If NVIDIA docker image is used you don't need to specify these.
Otherwise, please provide:

• Ubuntu 22.04
• PyTorch 2.2.1
• Python 3.10.0

Additional context

Add any other context about the problem here.
This is the hybrid RNNT CTC model.

[titu1994]

You are using the main branch Nemo inference scro "transcribe_search.py" whole having Nemo 1.23 or lower installed, that will not work.

Switch your branch to r1.23.0, then use the inference script in that version.