model upload

README.md

@@ -0,0 +1,20 @@
+---
+language:
+  - qvi
+  - qug
+license: cc-by-4.0
+tags:
+  - audio
+  - automatic-speech-recognition
+  - speech
+  - wav2vec2
+  - low-resource
+base_model:
+  - facebook/wav2vec2-large-xlsr-53
+---
+
+# Killkan-ASR
+
+Killkan (Kichwa uyashkata payLLatak Killkak ANta "Kichwa Automatic Speech Transcriber) is an automatic speech recognition dataset for Kichwa, and `Killkan-ASR` is the ASR model based on the dataset.
+
+

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 70,
+  "<s>": 69
+}

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": 68,
+  "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": "4.37.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 71,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7440b7cdc37ec9d3b4e499ade6a85c346038631efdfbe49936b361469953a41d
+size 1262098580

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,47 @@
+{
+  "added_tokens_decoder": {
+    "67": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "70": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": " "
+}

vocab.json

@@ -0,0 +1,71 @@
+{
+  " ": 48,
+  "!": 47,
+  ",": 5,
+  ".": 2,
+  "?": 41,
+  "A": 0,
+  "B": 31,
+  "C": 4,
+  "D": 27,
+  "E": 39,
+  "F": 55,
+  "G": 50,
+  "H": 7,
+  "I": 46,
+  "J": 17,
+  "K": 30,
+  "L": 52,
+  "M": 63,
+  "N": 54,
+  "O": 43,
+  "P": 21,
+  "Q": 28,
+  "R": 22,
+  "S": 57,
+  "T": 61,
+  "U": 36,
+  "V": 14,
+  "W": 59,
+  "Y": 65,
+  "Z": 34,
+  "[": 18,
+  "[PAD]": 68,
+  "[UNK]": 67,
+  "]": 3,
+  "a": 12,
+  "b": 60,
+  "c": 51,
+  "d": 11,
+  "e": 19,
+  "f": 13,
+  "g": 49,
+  "h": 66,
+  "i": 10,
+  "j": 24,
+  "k": 44,
+  "l": 37,
+  "m": 38,
+  "n": 20,
+  "o": 15,
+  "p": 32,
+  "q": 1,
+  "r": 56,
+  "s": 40,
+  "t": 8,
+  "u": 25,
+  "v": 58,
+  "w": 9,
+  "x": 16,
+  "y": 42,
+  "z": 26,
+  " ": 64,
+  "Ñ": 62,
+  "á": 29,
+  "é": 33,
+  "í": 53,
+  "ñ": 6,
+  "ó": 45,
+  "ú": 35,
+  "ü": 23
+}