add files

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "s2t_mustc_multilingual_medium",
+  "activation_dropout": 0.15,
+  "activation_function": "relu",
+  "architectures": [
+    "Speech2TextTransformerForConditionalGeneration"
+  ],
+  "attention_dropout": 0.15,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.0,
+  "conv_channels": 1024,
+  "conv_kernel_sizes": [
+    5,
+    5
+  ],
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.15,
+  "early_stopping": true,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "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_transformer",
+  "num_beams": 5,
+  "num_conv_layers": 2,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.4.0.dev0",
+  "use_cache": true,
+  "vocab_size": 10000
+}

preprocessor_config.json

@@ -0,0 +1,11 @@
+{
+  "do_normalize": true,
+  "feature_size": 80,
+  "norm_means": true,
+  "norm_vars": true,
+  "num_mel_bins": 80,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fb66c18867902d4b639e529a2eaac152edff9ba0f2d6475686a657f05104809
+size 305448471

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccd9bc57fef83ec633abb6496fa47c9660891b9acca2b487671395dba2173772
+size 410393

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<lang:pt>", "<lang:fr>", "<lang:ru>", "<lang:nl>", "<lang:ro>", "<lang:it>", "<lang:es>", "<lang:de>"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "do_upper_case": false, "tgt_lang": null, "lang_codes": "mustc"}