Unable to decode using canary 1b model

[uni-saurabh-vyas]

Describe the bug

A clear and concise description of what the bug is.

I am using nemo inside docker environment, with single GPU, unable to get the ASR ouput using canary 1b model

Error executing job with overrides: ['pretrained_name=nvidia/canary-1b', 'audio_dir=/opt/workspace/es_test', 'output_filename=canary_output.txt', 'clean_groundtruth_text=True', 'langid=es', 'batch_size=1', 'compute_timestamps=False', 'compute_langs=False', 'cuda=0', 'amp=True', 'append_pred=False', 'pred_name_postfix=canary']
Traceback (most recent call last):
  File "/opt/asr_ensemble/repo/nemo/examples/asr/transcribe_speech.py", line 290, in main
    asr_model.change_decoding_strategy(cfg.ctc_decoding)
  File "/usr/local/lib/python3.10/dist-packages/nemo/collections/asr/models/aed_multitask_models.py", line 203, in change_decoding_strategy
    self.decoding = MultiTaskDecoding(
  File "/usr/local/lib/python3.10/dist-packages/nemo/collections/asr/parts/submodules/multitask_decoding.py", line 377, in __init__
    super().__init__(
  File "/usr/local/lib/python3.10/dist-packages/nemo/collections/asr/parts/submodules/multitask_decoding.py", line 124, in __init__
    raise NotImplementedError("Greedy decoding is not implemented yet.")
NotImplementedError: Greedy decoding is not implemented yet.

Steps/Code to reproduce bug

python3 nemo/examples/asr/transcribe_speech.py \
pretrained_name="nvidia/canary-1b" \
audio_dir="/opt/workspace/es_test" \
output_filename="canary_output.txt" \
clean_groundtruth_text=True \
langid='es' \
batch_size=1 \
compute_timestamps=False \
compute_langs=False \
cuda=0 \
amp=True \
append_pred=False \
pred_name_postfix="canary"

Expected behavior

A clear and concise description of what you expected to happen.

Environment overview (please complete the following information)

• Environment location: [Bare-metal, Docker, Cloud(specify cloud provider - AWS, Azure, GCP, Collab)]
• Method of NeMo install: [pip install or from source]. Please specify exact commands you used to install.
• If method of install is [Docker], provide docker pull & docker run commands used

Environment details

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

• OS version Ubuntu 20
• PyTorch version
• Python version 3.10

Additional context

Add any other context about the problem here.
Example: GPU model

[pzelasko]

Which NeMo version is this? Greedy decoding for Canary should work if you install the latest 2.0 pre-release, or the latest main branch.