Upload folder using huggingface_hub

README.md

@@ -1 +1,102 @@
-# Simba-M
+---
+license: cc-by-nc-4.0
+base_model: facebook/mms-1b-all
+tags:
+- automatic-speech-recognition
+- /mnt/home/elmadany/elmadany_workspace/African_speechT5/jasmine-raid/elmadany_work/HF_format/SimbaBench_tasks_ft
+- mms
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: mms-1b-all
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# mms-1b-all
+
+This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the /MNT/HOME/ELMADANY/ELMADANY_WORKSPACE/AFRICAN_SPEECHT5/JASMINE-RAID/ELMADANY_WORK/HF_FORMAT/SIMBABENCH_TASKS_FT - ASR_FT_DATA_BATCH_2 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2214
+- Wer: 0.2988
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.001
+- train_batch_size: 4
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 30.0
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Wer    |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|
+| 6.7354        | 1.0   | 610   | 0.5166          | 0.5255 |
+| 0.7031        | 2.0   | 1221  | 0.4340          | 0.4949 |
+| 0.6258        | 3.0   | 1831  | 0.3713          | 0.4372 |
+| 0.5844        | 4.0   | 2442  | 0.3527          | 0.4214 |
+| 0.5615        | 5.0   | 3053  | 0.3429          | 0.4238 |
+| 0.5829        | 2.0   | 4884  | 0.3453          | 0.4082 |
+| 0.5516        | 3.0   | 7327  | 0.3249          | 0.3986 |
+| 0.5313        | 4.0   | 9769  | 0.3149          | 0.3898 |
+| 0.5141        | 5.0   | 12212 | 0.3006          | 0.3754 |
+| 0.4991        | 6.0   | 14654 | 0.2959          | 0.3730 |
+| 0.4916        | 7.0   | 17097 | 0.2914          | 0.3667 |
+| 0.48          | 8.0   | 19539 | 0.2791          | 0.3528 |
+| 0.4708        | 9.0   | 21982 | 0.2808          | 0.3624 |
+| 0.4659        | 10.0  | 24424 | 0.2730          | 0.3518 |
+| 0.4587        | 11.0  | 26867 | 0.2708          | 0.3511 |
+| 0.4541        | 12.0  | 29309 | 0.2630          | 0.3371 |
+| 0.4442        | 13.0  | 31752 | 0.2606          | 0.3394 |
+| 0.439         | 14.0  | 34194 | 0.2592          | 0.3384 |
+| 0.4334        | 15.0  | 36637 | 0.2499          | 0.3300 |
+| 0.4304        | 16.0  | 39079 | 0.2492          | 0.3279 |
+| 0.4247        | 17.0  | 41522 | 0.2433          | 0.3255 |
+| 0.4197        | 18.0  | 43964 | 0.2407          | 0.3214 |
+| 0.4139        | 19.0  | 46407 | 0.2419          | 0.3172 |
+| 0.4091        | 20.0  | 48849 | 0.2378          | 0.3190 |
+| 0.4064        | 21.0  | 51292 | 0.2345          | 0.3150 |
+| 0.4026        | 22.0  | 53734 | 0.2319          | 0.3141 |
+| 0.4015        | 23.0  | 56177 | 0.2299          | 0.3070 |
+| 0.3941        | 24.0  | 58619 | 0.2278          | 0.3064 |
+| 0.3913        | 25.0  | 61062 | 0.2250          | 0.3044 |
+| 0.3902        | 26.0  | 63504 | 0.2270          | 0.3061 |
+| 0.3847        | 27.0  | 65947 | 0.2237          | 0.3025 |
+| 0.3826        | 28.0  | 68389 | 0.2214          | 0.2988 |
+| 0.3797        | 29.0  | 70832 | 0.2213          | 0.3001 |
+| 0.3786        | 29.99 | 73260 | 0.2208          | 0.2989 |
+
+
+### Framework versions
+
+- Transformers 4.33.2
+- Pytorch 2.0.1+cu117
+- Datasets 3.5.1
+- Tokenizers 0.13.3

adapter.multilingual_african.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b31b181215ee1591c2395ab7c3bc43537e515b9a864c4d7a7e11cdf820bd53f
+size 10832872

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 427,
+  "<s>": 426
+}

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": 0.05,
+  "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": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.05,
+  "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": 425,
+  "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": "4.33.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 428,
+  "xvector_output_dim": 512
+}

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5670e00ab5a3e126af3608015a7b0b18ffe537e75d0f58d6453cf62488824c7
+size 3861168781

special_tokens_map.json

@@ -0,0 +1,120 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "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": "multilingual_african",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 29.99,
+    "train_loss": 0.4226855478747569,
+    "train_runtime": 82629.0475,
+    "train_samples": 156308,
+    "train_samples_per_second": 56.751,
+    "train_steps_per_second": 0.887
+}

vocab.json

@@ -0,0 +1,430 @@
+{
+  "multilingual_african": {
+    "<": 1,
+    "=": 2,
+    ">": 3,
+    "[": 4,
+    "[PAD]": 425,
+    "[UNK]": 424,
+    "\\": 5,
+    "]": 6,
+    "_": 7,
+    "`": 8,
+    "a": 9,
+    "b": 10,
+    "c": 11,
+    "d": 12,
+    "e": 13,
+    "f": 14,
+    "g": 15,
+    "h": 16,
+    "i": 17,
+    "j": 18,
+    "k": 19,
+    "l": 20,
+    "m": 21,
+    "n": 22,
+    "o": 23,
+    "p": 24,
+    "q": 25,
+    "r": 26,
+    "s": 27,
+    "t": 28,
+    "u": 29,
+    "v": 30,
+    "w": 31,
+    "x": 32,
+    "y": 33,
+    "z": 34,
+    "|": 0,
+    "~": 35,
+    "«": 36,
+    "²": 37,
+    "µ": 38,
+    "·": 39,
+    "»": 40,
+    "à": 41,
+    "á": 42,
+    "â": 43,
+    "ã": 44,
+    "ç": 45,
+    "è": 46,
+    "é": 47,
+    "ê": 48,
+    "ë": 49,
+    "ì": 50,
+    "í": 51,
+    "ï": 52,
+    "ñ": 53,
+    "ò": 54,
+    "ó": 55,
+    "ô": 56,
+    "õ": 57,
+    "ö": 58,
+    "ù": 59,
+    "ú": 60,
+    "û": 61,
+    "ć": 62,
+    "č": 63,
+    "ĕ": 64,
+    "ğ": 65,
+    "ĩ": 66,
+    "ī": 67,
+    "ĭ": 68,
+    "ĺ": 69,
+    "ń": 70,
+    "ŋ": 71,
+    "ŏ": 72,
+    "ś": 73,
+    "š": 74,
+    "ŧ": 75,
+    "ũ": 76,
+    "ŭ": 77,
+    "ŵ": 78,
+    "ƙ": 79,
+    "ƥ": 80,
+    "ƭ": 81,
+    "ƴ": 82,
+    "ǧ": 83,
+    "ǹ": 84,
+    "ɓ": 85,
+    "ɔ": 86,
+    "ɖ": 87,
+    "ɗ": 88,
+    "ɛ": 89,
+    "ɣ": 90,
+    "ɲ": 91,
+    "ʹ": 92,
+    "ʻ": 93,
+    "̀": 94,
+    "́": 95,
+    "̆": 96,
+    "̈": 97,
+    "̣": 98,
+    "έ": 99,
+    "γ": 100,
+    "ε": 101,
+    "ԑ": 102,
+    "ሀ": 103,
+    "ሁ": 104,
+    "ሂ": 105,
+    "ሃ": 106,
+    "ሄ": 107,
+    "ህ": 108,
+    "ሆ": 109,
+    "ለ": 110,
+    "ሉ": 111,
+    "ሊ": 112,
+    "ላ": 113,
+    "ሌ": 114,
+    "ል": 115,
+    "ሎ": 116,
+    "ሏ": 117,
+    "ሐ": 118,
+    "ሑ": 119,
+    "ሒ": 120,
+    "ሓ": 121,
+    "ሔ": 122,
+    "ሕ": 123,
+    "ሖ": 124,
+    "መ": 125,
+    "ሙ": 126,
+    "ሚ": 127,
+    "ማ": 128,
+    "ሜ": 129,
+    "ም": 130,
+    "ሞ": 131,
+    "ሟ": 132,
+    "ሠ": 133,
+    "ሡ": 134,
+    "ሣ": 135,
+    "ሥ": 136,
+    "ሦ": 137,
+    "ረ": 138,
+    "ሩ": 139,
+    "ሪ": 140,
+    "ራ": 141,
+    "ሬ": 142,
+    "ር": 143,
+    "ሮ": 144,
+    "ሯ": 145,
+    "ሰ": 146,
+    "ሱ": 147,
+    "ሲ": 148,
+    "ሳ": 149,
+    "ሴ": 150,
+    "ስ": 151,
+    "ሶ": 152,
+    "ሷ": 153,
+    "ሸ": 154,
+    "ሹ": 155,
+    "ሺ": 156,
+    "ሻ": 157,
+    "ሼ": 158,
+    "ሽ": 159,
+    "ሾ": 160,
+    "ሿ": 161,
+    "ቀ": 162,
+    "ቁ": 163,
+    "ቂ": 164,
+    "ቃ": 165,
+    "ቄ": 166,
+    "ቅ": 167,
+    "ቆ": 168,
+    "ቋ": 169,
+    "ቐ": 170,
+    "ቒ": 171,
+    "ቓ": 172,
+    "ቕ": 173,
+    "ቚ": 174,
+    "በ": 175,
+    "ቡ": 176,
+    "ቢ": 177,
+    "ባ": 178,
+    "ቤ": 179,
+    "ብ": 180,
+    "ቦ": 181,
+    "ቧ": 182,
+    "ቨ": 183,
+    "ቩ": 184,
+    "ቪ": 185,
+    "ቫ": 186,
+    "ቬ": 187,
+    "ቭ": 188,
+    "ቮ": 189,
+    "ቯ": 190,
+    "ተ": 191,
+    "ቱ": 192,
+    "ቲ": 193,
+    "ታ": 194,
+    "ቴ": 195,
+    "ት": 196,
+    "ቶ": 197,
+    "ቷ": 198,
+    "ቸ": 199,
+    "ቹ": 200,
+    "ቺ": 201,
+    "ቻ": 202,
+    "ቼ": 203,
+    "ች": 204,
+    "ቾ": 205,
+    "ቿ": 206,
+    "ኃ": 207,
+    "ኅ": 208,
+    "ኋ": 209,
+    "ነ": 210,
+    "ኑ": 211,
+    "ኒ": 212,
+    "ና": 213,
+    "ኔ": 214,
+    "ን": 215,
+    "ኖ": 216,
+    "ኗ": 217,
+    "ኘ": 218,
+    "ኙ": 219,
+    "ኚ": 220,
+    "ኛ": 221,
+    "ኜ": 222,
+    "ኝ": 223,
+    "ኞ": 224,
+    "ኟ": 225,
+    "አ": 226,
+    "ኡ": 227,
+    "ኢ": 228,
+    "ኣ": 229,
+    "ኤ": 230,
+    "እ": 231,
+    "ኦ": 232,
+    "ከ": 233,
+    "ኩ": 234,
+    "ኪ": 235,
+    "ካ": 236,
+    "ኬ": 237,
+    "ክ": 238,
+    "ኮ": 239,
+    "ኰ": 240,
+    "ኲ": 241,
+    "ኳ": 242,
+    "ኸ": 243,
+    "ኻ": 244,
+    "ኽ": 245,
+    "ኾ": 246,
+    "ወ": 247,
+    "ዉ": 248,
+    "ዊ": 249,
+    "ዋ": 250,
+    "ዌ": 251,
+    "ው": 252,
+    "ዎ": 253,
+    "ዐ": 254,
+    "ዑ": 255,
+    "ዒ": 256,
+    "ዓ": 257,
+    "ዔ": 258,
+    "ዕ": 259,
+    "ዖ": 260,
+    "ዘ": 261,
+    "ዙ": 262,
+    "ዚ": 263,
+    "ዛ": 264,
+    "ዜ": 265,
+    "ዝ": 266,
+    "ዞ": 267,
+    "ዟ": 268,
+    "ዠ": 269,
+    "ዡ": 270,
+    "ዢ": 271,
+    "ዣ": 272,
+    "ዤ": 273,
+    "ዥ": 274,
+    "ዦ": 275,
+    "ዧ": 276,
+    "የ": 277,
+    "ዩ": 278,
+    "ዪ": 279,
+    "ያ": 280,
+    "ዬ": 281,
+    "ይ": 282,
+    "ዮ": 283,
+    "ደ": 284,
+    "ዱ": 285,
+    "ዲ": 286,
+    "ዳ": 287,
+    "ዴ": 288,
+    "ድ": 289,
+    "ዶ": 290,
+    "ዷ": 291,
+    "ጀ": 292,
+    "ጁ": 293,
+    "ጂ": 294,
+    "ጃ": 295,
+    "ጄ": 296,
+    "ጅ": 297,
+    "ጆ": 298,
+    "ጇ": 299,
+    "ገ": 300,
+    "ጉ": 301,
+    "ጊ": 302,
+    "ጋ": 303,
+    "ጌ": 304,
+    "ግ": 305,
+    "ጎ": 306,
+    "ጐ": 307,
+    "ጓ": 308,
+    "ጔ": 309,
+    "ጠ": 310,
+    "ጡ": 311,
+    "ጢ": 312,
+    "ጣ": 313,
+    "ጤ": 314,
+    "ጥ": 315,
+    "ጦ": 316,
+    "ጧ": 317,
+    "ጨ": 318,
+    "ጩ": 319,
+    "ጪ": 320,
+    "ጫ": 321,
+    "ጬ": 322,
+    "ጭ": 323,
+    "ጮ": 324,
+    "ጯ": 325,
+    "ጰ": 326,
+    "ጱ": 327,
+    "ጲ": 328,
+    "ጳ": 329,
+    "ጴ": 330,
+    "ጵ": 331,
+    "ጶ": 332,
+    "ጸ": 333,
+    "ጹ": 334,
+    "ጺ": 335,
+    "ጻ": 336,
+    "ጼ": 337,
+    "ጽ": 338,
+    "ጾ": 339,
+    "ጿ": 340,
+    "ፀ": 341,
+    "ፁ": 342,
+    "ፃ": 343,
+    "ፅ": 344,
+    "ፈ": 345,
+    "ፉ": 346,
+    "ፊ": 347,
+    "ፋ": 348,
+    "ፌ": 349,
+    "ፍ": 350,
+    "ፎ": 351,
+    "ፏ": 352,
+    "ፐ": 353,
+    "ፑ": 354,
+    "ፒ": 355,
+    "ፓ": 356,
+    "ፔ": 357,
+    "ፕ": 358,
+    "ፖ": 359,
+    "፡": 360,
+    "።": 361,
+    "፣": 362,
+    "፤": 363,
+    "ḅ": 364,
+    "ḍ": 365,
+    "ḓ": 366,
+    "ḥ": 367,
+    "ḷ": 368,
+    "ḽ": 369,
+    "ṅ": 370,
+    "ṋ": 371,
+    "ṕ": 372,
+    "ṛ": 373,
+    "ṣ": 374,
+    "ṭ": 375,
+    "ṱ": 376,
+    "ẃ": 377,
+    "ẓ": 378,
+    "ạ": 379,
+    "ẹ": 380,
+    "ị": 381,
+    "ọ": 382,
+    "ụ": 383,
+    "ὲ": 384,
+    "–": 385,
+    "—": 386,
+    "’": 387,
+    "‟": 388,
+    "•": 389,
+    "…": 390,
+    "‽": 391,
+    "ⴰ": 392,
+    "ⴱ": 393,
+    "ⴳ": 394,
+    "ⴷ": 395,
+    "ⴹ": 396,
+    "ⴻ": 397,
+    "ⴼ": 398,
+    "ⴽ": 399,
+    "ⵀ": 400,
+    "ⵃ": 401,
+    "ⵄ": 402,
+    "ⵅ": 403,
+    "ⵇ": 404,
+    "ⵉ": 405,
+    "ⵊ": 406,
+    "ⵍ": 407,
+    "ⵎ": 408,
+    "ⵏ": 409,
+    "ⵓ": 410,
+    "ⵔ": 411,
+    "ⵕ": 412,
+    "ⵖ": 413,
+    "ⵙ": 414,
+    "ⵚ": 415,
+    "ⵛ": 416,
+    "ⵜ": 417,
+    "ⵟ": 418,
+    "ⵡ": 419,
+    "ⵢ": 420,
+    "ⵣ": 421,
+    "ⵥ": 422,
+    "ⵯ": 423
+  }
+}