|
|
|
|
|
|
|
nb_tokens: 500 |
|
blank_index: 0 |
|
sample_rate: 16000 |
|
wav2vec2_hub: LeBenchmark/wav2vec2-FR-7K-large |
|
wav2vec_output_dim: 1024 |
|
nb_enc_neurons: 1024 |
|
enc_drop_out: 0.25 |
|
|
|
|
|
|
|
tokenizer: !new:sentencepiece.SentencePieceProcessor |
|
|
|
wav2vec2: !new:speechbrain.lobes.models.huggingface_wav2vec.HuggingFaceWav2Vec2 |
|
source: !ref <wav2vec2_hub> |
|
output_norm: True |
|
freeze: True |
|
save_path: pretrained_models |
|
|
|
enc: !new:speechbrain.nnet.containers.Sequential |
|
input_shape: [null, null, !ref <wav2vec_output_dim>] |
|
linear1: !name:speechbrain.nnet.linear.Linear |
|
n_neurons: !ref <nb_enc_neurons> |
|
bias: True |
|
bn1: !name:speechbrain.nnet.normalization.BatchNorm1d |
|
activation: !new:torch.nn.LeakyReLU |
|
drop: !new:torch.nn.Dropout |
|
p: !ref <enc_drop_out> |
|
linear2: !name:speechbrain.nnet.linear.Linear |
|
n_neurons: !ref <nb_enc_neurons> |
|
bias: True |
|
bn2: !name:speechbrain.nnet.normalization.BatchNorm1d |
|
activation2: !new:torch.nn.LeakyReLU |
|
drop2: !new:torch.nn.Dropout |
|
p: !ref <enc_drop_out> |
|
linear3: !name:speechbrain.nnet.linear.Linear |
|
n_neurons: !ref <nb_enc_neurons> |
|
bias: True |
|
bn3: !name:speechbrain.nnet.normalization.BatchNorm1d |
|
activation3: !new:torch.nn.LeakyReLU |
|
|
|
ctc_lin: !new:speechbrain.nnet.linear.Linear |
|
input_size: !ref <nb_enc_neurons> |
|
n_neurons: !ref <nb_tokens> |
|
|
|
decoding_function: !name:speechbrain.decoders.ctc_greedy_decode |
|
blank_id: !ref <blank_index> |
|
|
|
encoder: !new:speechbrain.nnet.containers.LengthsCapableSequential |
|
wav2vec2: !ref <wav2vec2> |
|
enc: !ref <enc> |
|
ctc_lin: !ref <ctc_lin> |
|
|
|
modules: |
|
encoder: !ref <encoder> |
|
|
|
asr_model: !new:torch.nn.ModuleList |
|
- [!ref <enc>, !ref <ctc_lin>] |
|
|
|
pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer |
|
loadables: |
|
wav2vec2: !ref <wav2vec2> |
|
asr: !ref <asr_model> |
|
tokenizer: !ref <tokenizer> |
|
|