Delete hyperparams_develop.yaml

hyperparams_develop.yaml

@@ -1,168 +0,0 @@
-# ############################################################################
-# Model: E2E ASR with attention-based ASR
-# Encoder: CRDNN model
-# Decoder: GRU + beamsearch + RNNLM
-# Tokens: BPE with unigram
-# Authors:  Ju-Chieh Chou, Mirco Ravanelli, Abdel Heba, Peter Plantinga 2020, Adel Moumen 2024
-# ############################################################################
-
-
-# Feature parameters
-sample_rate: 16000
-n_fft: 400
-n_mels: 40
-
-# Model parameters
-activation: !name:torch.nn.LeakyReLU
-dropout: 0.15
-cnn_blocks: 2
-cnn_channels: (128, 256)
-inter_layer_pooling_size: (2, 2)
-cnn_kernelsize: (3, 3)
-time_pooling_size: 4
-rnn_class: !name:speechbrain.nnet.RNN.LSTM
-rnn_layers: 4
-rnn_neurons: 1024
-rnn_bidirectional: True
-dnn_blocks: 2
-dnn_neurons: 512
-emb_size: 128
-dec_neurons: 1024
-output_neurons: 1000  # index(blank/eos/bos) = 0
-blank_index: 0
-
-# Decoding parameters
-bos_index: 0
-eos_index: 0
-min_decode_ratio: 0.0
-max_decode_ratio: 1.0
-beam_size: 80
-eos_threshold: 1.5
-using_max_attn_shift: True
-max_attn_shift: 240
-lm_weight: 0.50
-coverage_penalty: 1.5
-temperature: 1.25
-temperature_lm: 1.25
-
-normalizer: !new:speechbrain.processing.features.InputNormalization
-    norm_type: global
-
-compute_features: !new:speechbrain.lobes.features.Fbank
-    sample_rate: !ref <sample_rate>
-    n_fft: !ref <n_fft>
-    n_mels: !ref <n_mels>
-
-enc: !new:speechbrain.lobes.models.CRDNN.CRDNN
-    input_shape: [null, null, !ref <n_mels>]
-    activation: !ref <activation>
-    dropout: !ref <dropout>
-    cnn_blocks: !ref <cnn_blocks>
-    cnn_channels: !ref <cnn_channels>
-    cnn_kernelsize: !ref <cnn_kernelsize>
-    inter_layer_pooling_size: !ref <inter_layer_pooling_size>
-    time_pooling: True
-    using_2d_pooling: False
-    time_pooling_size: !ref <time_pooling_size>
-    rnn_class: !ref <rnn_class>
-    rnn_layers: !ref <rnn_layers>
-    rnn_neurons: !ref <rnn_neurons>
-    rnn_bidirectional: !ref <rnn_bidirectional>
-    rnn_re_init: True
-    dnn_blocks: !ref <dnn_blocks>
-    dnn_neurons: !ref <dnn_neurons>
-
-emb: !new:speechbrain.nnet.embedding.Embedding
-    num_embeddings: !ref <output_neurons>
-    embedding_dim: !ref <emb_size>
-
-dec: !new:speechbrain.nnet.RNN.AttentionalRNNDecoder
-    enc_dim: !ref <dnn_neurons>
-    input_size: !ref <emb_size>
-    rnn_type: gru
-    attn_type: location
-    hidden_size: !ref <dec_neurons>
-    attn_dim: 1024
-    num_layers: 1
-    scaling: 1.0
-    channels: 10
-    kernel_size: 100
-    re_init: True
-    dropout: !ref <dropout>
-
-ctc_lin: !new:speechbrain.nnet.linear.Linear
-    input_size: !ref <dnn_neurons>
-    n_neurons: !ref <output_neurons>
-
-seq_lin: !new:speechbrain.nnet.linear.Linear
-    input_size: !ref <dec_neurons>
-    n_neurons: !ref <output_neurons>
-
-log_softmax: !new:speechbrain.nnet.activations.Softmax
-    apply_log: True
-
-lm_model: !new:speechbrain.lobes.models.RNNLM.RNNLM
-    output_neurons: !ref <output_neurons>
-    embedding_dim: !ref <emb_size>
-    activation: !name:torch.nn.LeakyReLU
-    dropout: 0.0
-    rnn_layers: 2
-    rnn_neurons: 2048
-    dnn_blocks: 1
-    dnn_neurons: 512
-    return_hidden: True  # For inference
-
-tokenizer: !new:sentencepiece.SentencePieceProcessor
-
-asr_model: !new:torch.nn.ModuleList
-    - [!ref <enc>, !ref <emb>, !ref <dec>, !ref <ctc_lin>, !ref <seq_lin>]
-
-# We compose the inference (encoder) pipeline.
-encoder: !new:speechbrain.nnet.containers.LengthsCapableSequential
-    input_shape: [null, null, !ref <n_mels>]
-    compute_features: !ref <compute_features>
-    normalize: !ref <normalizer>
-    model: !ref <enc>
-
-# Scorer
-coverage_scorer: !new:speechbrain.decoders.scorer.CoverageScorer
-   vocab_size: !ref <output_neurons>
-
-rnnlm_scorer: !new:speechbrain.decoders.scorer.RNNLMScorer
-   language_model: !ref <lm_model>
-   temperature: !ref <temperature_lm>
-
-scorer: !new:speechbrain.decoders.scorer.ScorerBuilder
-   full_scorers: [!ref <rnnlm_scorer>,
-                  !ref <coverage_scorer>]
-   weights:
-      rnnlm: !ref <lm_weight>
-      coverage: !ref <coverage_penalty>
-
-decoder: !new:speechbrain.decoders.S2SRNNBeamSearcher
-   embedding: !ref <emb>
-   decoder: !ref <dec>
-   linear: !ref <seq_lin>
-   bos_index: !ref <bos_index>
-   eos_index: !ref <eos_index>
-   min_decode_ratio: !ref <min_decode_ratio>
-   max_decode_ratio: !ref <max_decode_ratio>
-   beam_size: !ref <beam_size>
-   eos_threshold: !ref <eos_threshold>
-   using_max_attn_shift: !ref <using_max_attn_shift>
-   max_attn_shift: !ref <max_attn_shift>
-   temperature: !ref <temperature>
-   scorer: !ref <scorer>
-
-modules:
-    normalizer: !ref <normalizer>
-    encoder: !ref <encoder>
-    decoder: !ref <decoder>
-    lm_model: !ref <lm_model>
-
-pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
-    loadables:
-        normalizer: !ref <normalizer>
-        asr: !ref <asr_model>
-        lm: !ref <lm_model>
-        tokenizer: !ref <tokenizer>