| # ################################ | |
| # 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: italian | |
| auto_mix_prec: False | |
| sample_rate: 16000 | |
| # These values are only used for the searchers. | |
| # They needs to be hardcoded and should not be changed with Whisper. | |
| # They are used as part of the searching process. | |
| # The bos token of the searcher will be timestamp_index | |
| # and will be concatenated with the bos, language and task tokens. | |
| timestamp_index: 50363 | |
| eos_index: 50257 | |
| bos_index: 50258 | |
| # Decoding parameters | |
| min_decode_ratio: 0.0 | |
| max_decode_ratio: 1.0 | |
| 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.S2SWhisperGreedySearch | |
| model: !ref <whisper> | |
| bos_index: !ref <timestamp_index> | |
| eos_index: !ref <eos_index> | |
| min_decode_ratio: !ref <min_decode_ratio> | |
| max_decode_ratio: !ref <max_decode_ratio> | |
| # test_beam_searcher: !new:speechbrain.decoders.seq2seq.S2SWhisperBeamSearch | |
| # module: [!ref <whisper>] | |
| # bos_index: !ref <timestamp_index> | |
| # eos_index: !ref <eos_index> | |
| # 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> | |