{
  "sample_rate": 16000,
  "log_prediction": true,
  "ctc_reduction": "mean_batch",
  "skip_nan_grad": false,
  "use_cer": true,
  "train_ds": {
    "manifest_filepath": "/kaggle/working/mono_nemo_train.json",
    "sample_rate": 16000,
    "batch_size": 4,
    "shuffle": true,
    "num_workers": 4,
    "pin_memory": true,
    "max_duration": 16.7,
    "min_duration": 0.1,
    "is_tarred": false,
    "tarred_audio_filepaths": null,
    "shuffle_n": 2048,
    "bucketing_strategy": "synced_randomized",
    "bucketing_batch_size": null
  },
  "validation_ds": {
    "manifest_filepath": "/kaggle/working/mono_nemo_val.json",
    "sample_rate": 16000,
    "batch_size": 4,
    "shuffle": false,
    "use_start_end_token": false,
    "num_workers": 4,
    "pin_memory": true
  },
  "test_ds": {
    "manifest_filepath": "/kaggle/working/mono_nemo_test.json",
    "sample_rate": 16000,
    "batch_size": 4,
    "shuffle": false,
    "use_start_end_token": false,
    "num_workers": 4,
    "pin_memory": true
  },
  "tokenizer": {
    "dir": "tokens/tokenizer_spe_unigram_v128_max_200",
    "type": "bpe",
    "model_path": "nemo:9a7d38387f7b45a7a6d1c51db1072cbd_tokenizer.model",
    "vocab_path": "nemo:6729022885274af79d49ebcacbc7b3d3_vocab.txt",
    "spe_tokenizer_vocab": "nemo:16d5c791dd5049f6a9d102a1cef238df_tokenizer.vocab"
  },
  "preprocessor": {
    "_target_": "nemo.collections.asr.modules.AudioToMelSpectrogramPreprocessor",
    "sample_rate": 16000,
    "normalize": "per_feature",
    "window_size": 0.025,
    "window_stride": 0.01,
    "window": "hann",
    "features": 80,
    "n_fft": 512,
    "log": true,
    "frame_splicing": 1,
    "dither": 1e-05,
    "pad_to": 0,
    "pad_value": 0.0
  },
  "spec_augment": {
    "_target_": "nemo.collections.asr.modules.SpectrogramAugmentation",
    "freq_masks": 2,
    "time_masks": 2,
    "freq_width": 27,
    "time_width": 70
  },
  "encoder": {
    "_target_": "nemo.collections.asr.modules.ConformerEncoder",
    "feat_in": 80,
    "feat_out": -1,
    "n_layers": 18,
    "d_model": 256,
    "subsampling": "striding",
    "subsampling_factor": 4,
    "subsampling_conv_channels": -1,
    "causal_downsampling": false,
    "ff_expansion_factor": 4,
    "self_attention_model": "rel_pos",
    "n_heads": 4,
    "att_context_size": [
      -1,
      -1
    ],
    "att_context_style": "regular",
    "xscaling": true,
    "untie_biases": true,
    "pos_emb_max_len": 5000,
    "conv_kernel_size": 31,
    "conv_norm_type": "batch_norm",
    "conv_context_size": null,
    "dropout": 0.1,
    "dropout_pre_encoder": 0.1,
    "dropout_emb": 0.0,
    "dropout_att": 0.1,
    "stochastic_depth_drop_prob": 0.0,
    "stochastic_depth_mode": "linear",
    "stochastic_depth_start_layer": 1
  },
  "decoder": {
    "_target_": "nemo.collections.asr.modules.ConvASRDecoder",
    "feat_in": 256,
    "num_classes": 128,
    "vocabulary": [
      "<unk>",
      "▁",
      "ा",
      "ि",
      "ं",
      "ल",
      "ु",
      "क",
      "ः",
      "त",
      "न",
      "स",
      "े",
      "या",
      "इ",
      "र",
      "्",
      "▁म",
      "्व",
      "गु",
      "म",
      "▁व",
      "्य",
      "य्",
      "ाः",
      "ह",
      "▁ख",
      "य",
      "▁क",
      "▁स",
      "▁ब",
      "▁त",
      "▁छ",
      "प",
      "ू",
      "▁प",
      "ख",
      "ी",
      "ये",
      "▁द",
      "▁थ",
      "▁न",
      "चा",
      "▁ध",
      "व",
      "थ",
      "▁ज",
      "म्ह",
      "ना",
      "ग",
      "▁अ",
      "ज",
      "ँ",
      "ब",
      "▁भ",
      "▁नं",
      "च",
      "▁च",
      "द",
      "यात",
      "▁जि",
      "लि",
      "ने",
      "उ",
      "फ",
      "ो",
      "।",
      "श",
      "ध",
      "भ",
      "छ",
      "ौ",
      "झ",
      "ट",
      "ै",
      "॑",
      "ष",
      "ण",
      "”",
      ",",
      "घ",
      "ृ",
      "ड",
      "-",
      "!",
      "?",
      "ॉ",
      ":",
      "ञ",
      "ॅ",
      "‘",
      "’",
      "ए",
      ".",
      "ङ",
      "॒",
      "ओ",
      "अ",
      "ठ",
      "/",
      "\"",
      "़",
      ")",
      "०",
      ";",
      "ऋ",
      "ढ",
      "१",
      "'",
      "_",
      "२",
      "(",
      "औ",
      "ई",
      "‍",
      "“",
      "ऱ",
      "a",
      "m",
      "आ",
      "ऎ",
      "ऐ",
      "४",
      "५",
      "६",
      "८",
      "९",
      "ḑ"
    ]
  },
  "interctc": {
    "loss_weights": [],
    "apply_at_layers": []
  },
  "optim": {
    "name": "adamw",
    "lr": 0.0001,
    "betas": [
      0.9,
      0.98
    ],
    "weight_decay": 0.001,
    "sched": {
      "name": "CosineAnnealing",
      "min_lr": 1e-06,
      "warmup_steps": 3000
    }
  },
  "target": "nemo.collections.asr.models.ctc_bpe_models.EncDecCTCModelBPE",
  "nemo_version": "2.1.0",
  "decoding": {
    "strategy": "greedy_batch",
    "preserve_alignments": null,
    "compute_timestamps": null,
    "word_seperator": " ",
    "segment_seperators": [
      ".",
      "!",
      "?"
    ],
    "segment_gap_threshold": null,
    "ctc_timestamp_type": "all",
    "batch_dim_index": 0,
    "greedy": {
      "preserve_alignments": false,
      "compute_timestamps": false,
      "preserve_frame_confidence": false,
      "confidence_method_cfg": {
        "name": "entropy",
        "entropy_type": "tsallis",
        "alpha": 0.33,
        "entropy_norm": "exp",
        "temperature": "DEPRECATED"
      }
    },
    "beam": {
      "beam_size": 4,
      "search_type": "default",
      "preserve_alignments": false,
      "compute_timestamps": false,
      "return_best_hypothesis": true,
      "beam_alpha": 1.0,
      "beam_beta": 0.0,
      "kenlm_path": null,
      "flashlight_cfg": {
        "lexicon_path": null,
        "boost_path": null,
        "beam_size_token": 16,
        "beam_threshold": 20.0,
        "unk_weight": -Infinity,
        "sil_weight": 0.0
      },
      "pyctcdecode_cfg": {
        "beam_prune_logp": -10.0,
        "token_min_logp": -5.0,
        "prune_history": false,
        "hotwords": null,
        "hotword_weight": 10.0
      }
    },
    "wfst": {
      "beam_size": 4,
      "search_type": "riva",
      "return_best_hypothesis": true,
      "preserve_alignments": false,
      "compute_timestamps": false,
      "decoding_mode": "nbest",
      "open_vocabulary_decoding": false,
      "beam_width": 10.0,
      "lm_weight": 1.0,
      "device": "cuda",
      "arpa_lm_path": null,
      "wfst_lm_path": null,
      "riva_decoding_cfg": {},
      "k2_decoding_cfg": {
        "search_beam": 20.0,
        "output_beam": 10.0,
        "min_active_states": 30,
        "max_active_states": 10000
      }
    },
    "confidence_cfg": {
      "preserve_frame_confidence": false,
      "preserve_token_confidence": false,
      "preserve_word_confidence": false,
      "exclude_blank": true,
      "aggregation": "min",
      "tdt_include_duration": false,
      "method_cfg": {
        "name": "entropy",
        "entropy_type": "tsallis",
        "alpha": 0.33,
        "entropy_norm": "exp",
        "temperature": "DEPRECATED"
      }
    },
    "temperature": 1.0
  }
}