Upload 10 files

README.md

@@ -0,0 +1,9 @@
+---
+license: apache-2.0
+language:
+- ki
+---
+These are trained model parameters for voice recognition of farmer queries in kikuyu. 
+The model has been trained on 44 hours of data collected collaboratively as part of AIEP project by Karya and Digital Green.
+
+the data can be downloaded from the link here: https://drive.google.com/drive/folders/1fAY8kgd6ug35gf3DbCsQhX9MSdoURJu5?usp=drive_link

adapter.kik.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68e73909930b27e43f31087f881be17ded6d926fdd8e6e0aa936e4b8a6f9222f
+size 132

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 58,
+  "<s>": 57
+}

config.json

@@ -0,0 +1,108 @@
+{
+  "_name_or_path": "facebook/mms-1b-all",
+  "activation_dropout": 0.05,
+  "adapter_attn_dim": 16,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 1024,
+  "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": 0.05,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "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": 0.05,
+  "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": 48,
+  "num_negatives": 100,
+  "output_hidden_size": 1280,
+  "pad_token_id": 56,
+  "proj_codevector_dim": 1024,
+  "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": "4.44.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 59,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78cd93827470249041e99d1a17e5ccfc508f29b8586ef74df50907d6b3411472
+size 135

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
+}

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": {
+    "55": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "56": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "57": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58": {
+      "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": "kik",
+  "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:e106d19af9c0f7a676264bbf5b85db36d6f80d4c49043b941f162447fe597f88
+size 129

vocab.json

@@ -0,0 +1,61 @@
+{
+  "kik": {
+    "\n": 0,
+    "(": 2,
+    ")": 3,
+    "+": 4,
+    "/": 5,
+    "0": 6,
+    "1": 7,
+    "2": 8,
+    "3": 9,
+    "4": 10,
+    "5": 11,
+    "6": 12,
+    "7": 13,
+    "8": 14,
+    "9": 15,
+    "[PAD]": 56,
+    "[UNK]": 55,
+    "_": 16,
+    "a": 17,
+    "b": 18,
+    "c": 19,
+    "d": 20,
+    "e": 21,
+    "f": 22,
+    "g": 23,
+    "h": 24,
+    "i": 25,
+    "j": 26,
+    "k": 27,
+    "l": 28,
+    "m": 29,
+    "n": 30,
+    "o": 31,
+    "p": 32,
+    "r": 33,
+    "s": 34,
+    "t": 35,
+    "u": 36,
+    "v": 37,
+    "w": 38,
+    "x": 39,
+    "y": 40,
+    "z": 41,
+    "|": 1,
+    "®": 42,
+    "°": 43,
+    "³": 44,
+    "×": 45,
+    "í": 46,
+    "î": 47,
+    "ú": 48,
+    "û": 49,
+    "ĩ": 50,
+    "ī": 51,
+    "ũ": 52,
+    "ū": 53,
+    "–": 54
+  }
+}