hyperparams.yaml

# ################################
# Model: Whisper (Encoder-Decoder) + NLL
# Augmentation: TimeDomainSpecAugment
# Authors: Pooneh Mousavi 2022
# ################################


# URL for the biggest Fairseq english whisper model.
whisper_hub: openai/whisper-medium

# Normalize inputs with
# the same normalization done in the paper. Refer to Appendix C for further information.
normalized_transcripts: True

language: persian 

auto_mix_prec: False
sample_rate: 16000

# Decoding parameters
min_decode_ratio: 0.0
max_decode_ratio: 0.1
test_beam_size: 8

# Model parameters
freeze_whisper: True
freeze_encoder: True


whisper: !new:speechbrain.lobes.models.huggingface_transformers.whisper.Whisper
    source: !ref <whisper_hub>
    freeze: !ref <freeze_whisper>
    freeze_encoder: !ref <freeze_encoder>
    save_path: whisper_checkpoints
    encoder_only:  False

decoder: !new:speechbrain.decoders.seq2seq.S2SWhisperGreedySearcher
    model: !ref <whisper>
    min_decode_ratio: !ref <min_decode_ratio>
    max_decode_ratio: !ref <max_decode_ratio>

# test_beam_searcher: !new:speechbrain.decoders.seq2seq.S2SWhisperBeamSearcher
#     module: [!ref <whisper>]
#     min_decode_ratio: !ref <min_decode_ratio>
#     max_decode_ratio: !ref <max_decode_ratio>
#     beam_size: !ref <test_beam_size>

modules:
    whisper: !ref <whisper>
    decoder:  !ref <decoder>
 

pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
    loadables:
        whisper: !ref <whisper>