Upload with huggingface_hub

.gitattributes

@@ -30,3 +30,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+language_model/unigrams.txt filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1 @@
+{}

alphabet.json

@@ -0,0 +1 @@
+{"labels": [" ", "l", "o", "d", "a", "p", "w", "b", "y", "e", "i", "q", "x", "h", "c", "z", "f", "k", "u", "n", "s", "v", "t", "m", "j", "r", "g", "\u2047", ""], "is_bpe": false}

config.json

@@ -0,0 +1,107 @@
+{
+  "_name_or_path": "drive/MyDrive/PAPER_ASR_2/MODEL/xls-r-300m-ASR-idn-ALL/checkpoint-89400",
+  "activation_dropout": 0.0,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": true,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.3,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 28,
+  "proj_codevector_dim": 768,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.21.3",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 29,
+  "xvector_output_dim": 512
+}

language_model/2gram.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cb19220d2a3cad1a3ca0d68b33f428da1af42eecf393a512cdc7b6823a9ee37
+size 544464798

language_model/attrs.json

@@ -0,0 +1 @@
+{"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}

language_model/unigrams.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64040d0d7cecacce8ad7f48a3ac90bcb60710821b71c517db904a8fc9d166795
+size 32928244

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2ProcessorWithLM",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6434a676b197330d1a91aeb0ced5b00ad66d89ca65b9250b46a51311d865caab
+size 1262017585

special_tokens_map.json

@@ -0,0 +1,22 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": null,
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": null,
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": null,
+  "eos_token": null,
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token": null,
+  "do_lower_case": false,
+  "eos_token": null,
+  "name_or_path": "drive/MyDrive/PAPER_ASR_2/MODEL/xls-r-300m-ASR-idn-ALL",
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2ProcessorWithLM",
+  "replace_word_delimiter_char": " ",
+  "special_tokens_map_file": "drive/MyDrive/PAPER_ASR_2/MODEL/xls-r-300m-ASR-idn-ALL/special_tokens_map.json",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f70be5a727ba0d876487b37c0b9cb30d6117827fff121eb17158158f8593a877
+size 3375

vocab.json

@@ -0,0 +1,31 @@
+{
+  "[PAD]": 28,
+  "[UNK]": 27,
+  "a": 4,
+  "b": 7,
+  "c": 14,
+  "d": 3,
+  "e": 9,
+  "f": 16,
+  "g": 26,
+  "h": 13,
+  "i": 10,
+  "j": 24,
+  "k": 17,
+  "l": 1,
+  "m": 23,
+  "n": 19,
+  "o": 2,
+  "p": 5,
+  "q": 11,
+  "r": 25,
+  "s": 20,
+  "t": 22,
+  "u": 18,
+  "v": 21,
+  "w": 6,
+  "x": 12,
+  "y": 8,
+  "z": 15,
+  "|": 0
+}