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 +1,4 @@
+{
+  "</s>": 231,
+  "<s>": 230
+}

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": {
+    "228": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "229": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "230": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "231": {
+      "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 +1,232 @@
+{
+  "0": 1,
+  "1": 2,
+  "2": 3,
+  "3": 4,
+  "4": 5,
+  "5": 6,
+  "6": 7,
+  "7": 8,
+  "8": 9,
+  "9": 10,
+  "[PAD]": 229,
+  "[UNK]": 228,
+  "_": 11,
+  "r": 12,
+  "t": 13,
+  "|": 0,
+  "ሀ": 14,
+  "ሁ": 15,
+  "ሂ": 16,
+  "ሄ": 17,
+  "ህ": 18,
+  "ሆ": 19,
+  "ለ": 20,
+  "ሉ": 21,
+  "ሊ": 22,
+  "ላ": 23,
+  "ሌ": 24,
+  "ል": 25,
+  "ሎ": 26,
+  "ሏ": 27,
+  "መ": 28,
+  "ሙ": 29,
+  "ሚ": 30,
+  "ማ": 31,
+  "ሜ": 32,
+  "ም": 33,
+  "ሞ": 34,
+  "ሟ": 35,
+  "ረ": 36,
+  "ሩ": 37,
+  "ሪ": 38,
+  "ራ": 39,
+  "ሬ": 40,
+  "ር": 41,
+  "ሮ": 42,
+  "ሯ": 43,
+  "ሰ": 44,
+  "ሱ": 45,
+  "ሲ": 46,
+  "ሳ": 47,
+  "ሴ": 48,
+  "ስ": 49,
+  "ሶ": 50,
+  "ሷ": 51,
+  "ሸ": 52,
+  "ሹ": 53,
+  "ሺ": 54,
+  "ሻ": 55,
+  "ሼ": 56,
+  "ሽ": 57,
+  "ሾ": 58,
+  "ሿ": 59,
+  "ቀ": 60,
+  "ቁ": 61,
+  "ቂ": 62,
+  "ቃ": 63,
+  "ቄ": 64,
+  "ቅ": 65,
+  "ቆ": 66,
+  "ቋ": 67,
+  "በ": 68,
+  "ቡ": 69,
+  "ቢ": 70,
+  "ባ": 71,
+  "ቤ": 72,
+  "ብ": 73,
+  "ቦ": 74,
+  "ቧ": 75,
+  "ቨ": 76,
+  "ቩ": 77,
+  "ቪ": 78,
+  "ቫ": 79,
+  "ቬ": 80,
+  "ቭ": 81,
+  "ቮ": 82,
+  "ተ": 83,
+  "ቱ": 84,
+  "ቲ": 85,
+  "ታ": 86,
+  "ቴ": 87,
+  "ት": 88,
+  "ቶ": 89,
+  "ቷ": 90,
+  "ቸ": 91,
+  "ቹ": 92,
+  "ቺ": 93,
+  "ቻ": 94,
+  "ቼ": 95,
+  "ች": 96,
+  "ቾ": 97,
+  "ቿ": 98,
+  "ኋ": 99,
+  "ነ": 100,
+  "ኑ": 101,
+  "ኒ": 102,
+  "ና": 103,
+  "ኔ": 104,
+  "ን": 105,
+  "ኖ": 106,
+  "ኗ": 107,
+  "ኘ": 108,
+  "ኙ": 109,
+  "ኚ": 110,
+  "ኛ": 111,
+  "ኜ": 112,
+  "ኝ": 113,
+  "ኞ": 114,
+  "ኟ": 115,
+  "አ": 116,
+  "ኡ": 117,
+  "ኢ": 118,
+  "ኤ": 119,
+  "እ": 120,
+  "ኦ": 121,
+  "ከ": 122,
+  "ኩ": 123,
+  "ኪ": 124,
+  "ካ": 125,
+  "ኬ": 126,
+  "ክ": 127,
+  "ኮ": 128,
+  "ኰ": 129,
+  "ኲ": 130,
+  "ኳ": 131,
+  "ኸ": 132,
+  "ወ": 133,
+  "ዉ": 134,
+  "ዊ": 135,
+  "ዋ": 136,
+  "ዌ": 137,
+  "ው": 138,
+  "ዎ": 139,
+  "ዘ": 140,
+  "ዙ": 141,
+  "ዚ": 142,
+  "ዛ": 143,
+  "ዜ": 144,
+  "ዝ": 145,
+  "ዞ": 146,
+  "ዟ": 147,
+  "ዠ": 148,
+  "ዡ": 149,
+  "ዢ": 150,
+  "ዤ": 151,
+  "ዥ": 152,
+  "ዦ": 153,
+  "የ": 154,
+  "ዩ": 155,
+  "ዪ": 156,
+  "ያ": 157,
+  "ዬ": 158,
+  "ይ": 159,
+  "ዮ": 160,
+  "ደ": 161,
+  "ዱ": 162,
+  "ዲ": 163,
+  "ዳ": 164,
+  "ዴ": 165,
+  "ድ": 166,
+  "ዶ": 167,
+  "ዷ": 168,
+  "ጀ": 169,
+  "ጁ": 170,
+  "ጂ": 171,
+  "ጃ": 172,
+  "ጄ": 173,
+  "ጅ": 174,
+  "ጆ": 175,
+  "ጇ": 176,
+  "ገ": 177,
+  "ጉ": 178,
+  "ጊ": 179,
+  "ጋ": 180,
+  "ጌ": 181,
+  "ግ": 182,
+  "ጐ": 183,
+  "ጓ": 184,
+  "ጔ": 185,
+  "ጠ": 186,
+  "ጡ": 187,
+  "ጢ": 188,
+  "ጣ": 189,
+  "ጤ": 190,
+  "ጥ": 191,
+  "ጦ": 192,
+  "ጧ": 193,
+  "ጨ": 194,
+  "ጩ": 195,
+  "ጪ": 196,
+  "ጫ": 197,
+  "ጬ": 198,
+  "ጭ": 199,
+  "ጮ": 200,
+  "ጱ": 201,
+  "ጳ": 202,
+  "ጵ": 203,
+  "ጶ": 204,
+  "ጸ": 205,
+  "ጹ": 206,
+  "ጺ": 207,
+  "ጻ": 208,
+  "ጼ": 209,
+  "ጽ": 210,
+  "ጾ": 211,
+  "ጿ": 212,
+  "ፈ": 213,
+  "ፉ": 214,
+  "ፊ": 215,
+  "ፋ": 216,
+  "ፌ": 217,
+  "ፍ": 218,
+  "ፎ": 219,
+  "ፏ": 220,
+  "ፐ": 221,
+  "ፑ": 222,
+  "ፒ": 223,
+  "ፓ": 224,
+  "ፔ": 225,
+  "ፕ": 226,
+  "ፖ": 227
+}