Upload tokenizer

README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 173,
+  "<s>": 172,
+  "[PAD]": 171
+}

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 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "170": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "171": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "172": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "173": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "target_lang": "kik",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,176 @@
+{
+  "kik": {
+    "\n": 0,
+    "!": 2,
+    "\"": 3,
+    "#": 4,
+    "$": 5,
+    "%": 6,
+    "&": 7,
+    "'": 8,
+    "(": 9,
+    ")": 10,
+    "*": 11,
+    "+": 12,
+    ",": 13,
+    "-": 14,
+    ".": 15,
+    "/": 16,
+    "0": 17,
+    "1": 18,
+    "2": 19,
+    "3": 20,
+    "4": 21,
+    "5": 22,
+    "6": 23,
+    "7": 24,
+    "8": 25,
+    "9": 26,
+    ":": 27,
+    ";": 28,
+    "=": 29,
+    ">": 30,
+    "?": 31,
+    "@": 32,
+    "A": 33,
+    "B": 34,
+    "C": 35,
+    "D": 36,
+    "E": 37,
+    "F": 38,
+    "G": 39,
+    "H": 40,
+    "I": 41,
+    "J": 42,
+    "K": 43,
+    "L": 44,
+    "M": 45,
+    "N": 46,
+    "O": 47,
+    "P": 48,
+    "Q": 49,
+    "R": 50,
+    "S": 51,
+    "T": 52,
+    "U": 53,
+    "V": 54,
+    "W": 55,
+    "X": 56,
+    "Y": 57,
+    "Z": 58,
+    "[": 59,
+    "[PAD]": 171,
+    "[UNK]": 170,
+    "]": 60,
+    "_": 61,
+    "`": 62,
+    "a": 63,
+    "b": 64,
+    "c": 65,
+    "d": 66,
+    "e": 67,
+    "f": 68,
+    "g": 69,
+    "h": 70,
+    "i": 71,
+    "j": 72,
+    "k": 73,
+    "l": 74,
+    "m": 75,
+    "n": 76,
+    "o": 77,
+    "p": 78,
+    "q": 79,
+    "r": 80,
+    "s": 81,
+    "t": 82,
+    "u": 83,
+    "v": 84,
+    "w": 85,
+    "x": 86,
+    "y": 87,
+    "z": 88,
+    "{": 89,
+    "|": 1,
+    "}": 91,
+    "~": 92,
+    " ": 93,
+    "°": 94,
+    "´": 95,
+    "·": 96,
+    "Ç": 97,
+    "Ì": 98,
+    "Õ": 99,
+    "×": 100,
+    "Ù": 101,
+    "à": 102,
+    "á": 103,
+    "â": 104,
+    "ã": 105,
+    "ç": 106,
+    "è": 107,
+    "é": 108,
+    "ì": 109,
+    "í": 110,
+    "î": 111,
+    "ï": 112,
+    "ñ": 113,
+    "ò": 114,
+    "ó": 115,
+    "ô": 116,
+    "õ": 117,
+    "ö": 118,
+    "ù": 119,
+    "ú": 120,
+    "û": 121,
+    "ü": 122,
+    "ă": 123,
+    "ē": 124,
+    "ĥ": 125,
+    "Ĩ": 126,
+    "ĩ": 127,
+    "Ī": 128,
+    "ī": 129,
+    "İ": 130,
+    "ı": 131,
+    "ĵ": 132,
+    "ķ": 133,
+    "ō": 134,
+    "ŏ": 135,
+    "ŕ": 136,
+    "Ţ": 137,
+    "Ũ": 138,
+    "ũ": 139,
+    "Ū": 140,
+    "ū": 141,
+    "ŭ": 142,
+    "ů": 143,
+    "ű": 144,
+    "ŵ": 145,
+    "ƙ": 146,
+    "Ʈ": 147,
+    "ǐ": 148,
+    "ȃ": 149,
+    "ȟ": 150,
+    "ʻ": 151,
+    "́": 152,
+    "̂": 153,
+    "̃": 154,
+    "̄": 155,
+    "̅": 156,
+    "̆": 157,
+    "̛": 158,
+    "̰": 159,
+    "͂": 160,
+    "‐": 161,
+    "–": 162,
+    "—": 163,
+    "‘": 164,
+    "’": 165,
+    "“": 166,
+    "”": 167,
+    "…": 168,
+    "⁇": 169,
+    "✓": 170
+  }
+}