valhalla's picture
update processor and readme
a7472a9
{
"_name_or_path": "hf_models_fb/s2t-large-librispeech-asr/",
"activation_dropout": 0.2,
"activation_function": "relu",
"architectures": [
"Speech2TextForConditionalGeneration"
],
"attention_dropout": 0.2,
"bos_token_id": 0,
"classifier_dropout": 0.0,
"conv_channels": 1024,
"conv_kernel_sizes": [
5,
5
],
"d_model": 1024,
"decoder_attention_heads": 16,
"decoder_ffn_dim": 4096,
"decoder_layerdrop": 0.0,
"decoder_layers": 6,
"decoder_start_token_id": 2,
"dropout": 0.2,
"early_stopping": true,
"encoder_attention_heads": 16,
"encoder_ffn_dim": 4096,
"encoder_layerdrop": 0.0,
"encoder_layers": 12,
"eos_token_id": 2,
"gradient_checkpointing": false,
"init_std": 0.02,
"input_channels": 1,
"input_feat_per_channel": 80,
"is_encoder_decoder": true,
"max_length": 200,
"max_source_positions": 6000,
"max_target_positions": 1024,
"model_type": "speech_to_text",
"num_beams": 5,
"num_conv_layers": 2,
"num_hidden_layers": 12,
"pad_token_id": 1,
"scale_embedding": true,
"transformers_version": "4.4.0.dev0",
"use_cache": true,
"vocab_size": 10000
}