Upload folder using huggingface_hub

config.json

@@ -0,0 +1,117 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
+  "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": false,
+  "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,
+  "gradient_checkpointing": false,
+  "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_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "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_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "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": 63,
+  "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": "4.31.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 64,
+  "xvector_output_dim": 512
+}

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "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:e5d1d74cfb834b8e40eba61a96a6238bbab3049d8980ab325673d9150e29c6b2
+size 1262164269

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba48b1bafaf500372ab5fc832141629c1743fe9a93e8d0daf2f9837406566de7
+size 3963

vocab.json

@@ -0,0 +1 @@
+{"\u0930": 0, "\u094c": 1, "\u094b": 2, "\u0943": 3, "\u0941": 4, "\u090a": 5, "\u093e": 6, "\u0908": 7, "\u0918": 8, "\u091a": 9, "\u0924": 10, "\u0923": 12, "\u0920": 13, "\u0915": 14, "\u0917": 15, "\u0911": 16, "\u0921": 17, "\u092b": 18, "\u0907": 19, "\u093f": 20, "\u0937": 21, "\u092c": 22, "\u0906": 23, "\u092a": 24, "\u093c": 25, "\u0948": 26, "\u0902": 27, "\u0942": 28, "\u091b": 29, "\u094d": 30, "\u0928": 31, "\u090f": 32, "\u0938": 33, "\u0936": 34, "\u0905": 35, "\u0932": 36, "\u0940": 37, "\u091d": 38, "\u091c": 39, "\u0914": 40, "\u0909": 41, "\u0901": 42, "\u0945": 43, "\u0939": 44, "\u091f": 45, "\u0947": 46, "\u0910": 47, "\u092e": 48, "\u092d": 49, "\u0935": 50, "\u0927": 51, "\u091e": 52, "\u0916": 53, "\u0933": 54, "\u0926": 55, "\u0913": 56, "\u090b": 57, "\u092f": 58, "\u0925": 59, "\u0949": 60, "\u0922": 61, "|": 11, "[UNK]": 62, "[PAD]": 63}