| { | |
| "preprocessor": { | |
| "sample_rate": 16000, | |
| "normalize": "per_feature", | |
| "window_size": 0.025, | |
| "window_stride": 0.01, | |
| "window": "hann", | |
| "features": 128, | |
| "n_fft": 512, | |
| "dither": 1e-05, | |
| "pad_to": 0, | |
| "pad_value": 0.0, | |
| "preemph": 0.97, | |
| "mag_power": 2.0 | |
| }, | |
| "encoder": { | |
| "feat_in": 128, | |
| "n_layers": 32, | |
| "d_model": 1024, | |
| "n_heads": 8, | |
| "ff_expansion_factor": 4, | |
| "subsampling_factor": 8, | |
| "self_attention_model": "rel_pos", | |
| "subsampling": "dw_striding", | |
| "conv_kernel_size": 9, | |
| "subsampling_conv_channels": 256, | |
| "pos_emb_max_len": 5000, | |
| "causal_downsampling": false, | |
| "use_bias": true, | |
| "xscaling": false, | |
| "subsampling_conv_chunking_factor": 1, | |
| "att_context_size": [ | |
| -1, | |
| -1 | |
| ] | |
| }, | |
| "transf_decoder": { | |
| "vocab_size": 16384, | |
| "hidden_size": 1024, | |
| "inner_size": 4096, | |
| "num_layers": 8, | |
| "num_attention_heads": 8, | |
| "pre_ln": true, | |
| "hidden_act": "relu", | |
| "pre_ln_final_layer_norm": true, | |
| "learn_positional_encodings": false, | |
| "max_sequence_length": 1024 | |
| }, | |
| "head": { | |
| "num_layers": 1, | |
| "hidden_size": 1024, | |
| "num_classes": 16384 | |
| }, | |
| "prompt_format": "canary2", | |
| "tokenizer": { | |
| "type": "sentencepiece", | |
| "model_path": "tokenizer.model" | |
| } | |
| } |