End Training

README.md

@@ -0,0 +1,102 @@
+---
+base_model: ad019el/tamasheq-99-final
+datasets:
+- ad019el/ar_data
+- heisenberg1337/tamasheq_data
+metrics:
+- cer
+- wer
+tags:
+- generated_from_trainer
+---
+model-index:
+- name: tamasheq-99-final
+  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. -->
+
+# tamasheq-99-final
+
+This model is a fine-tuned version of [jonatasgrosman/wav2vec2-large-xlsr-53-arabic](https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-arabic) on the None dataset.
+It achieves the following results on the evaluation set:
+- Cer: 16.2959 
+- Wer: 55.5334 
+
+## 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: 3e-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+
+### Training results
+
+|step        |tamasheq_wer|arabic_wer|tamasheq_cer|arabic_cer|
+|------------|------------|----------|------------|----------|
+|Before train|104.985     |23.1305   |67.4458     |7.30972   |
+|step 300    |99.5513     |23.0544   |49.7078     |7.1043    |
+|step 600    |95.1147     |22.5267   |41.4515     |6.0098    |
+|step 900    |93.5194     |21.0404   |38.0867     |5.52939   |
+|step 1200   |92.5723     |20.6224   |37.0877     |5.39751   |
+|step 1500   |92.3009     |20.9238   |36.9915     |5.6718    |
+|step 1800   |92.0738     |21.2699   |36.3713     |6.08877   |
+|step 2100   |88.7338     |21.9693   |33.3648     |5.9156    |
+|step 2400   |87.1884     |21.1333   |31.8379     |5.52939   |
+|step 2700   |88.299      |21.0705   |31.4599     |5.5078    |
+|step 3000   |87.7866     |21.5021   |30.9039     |6.29239   |
+|step 3300   |84.2971     |21.666    |29.7455     |5.97212   |
+|step 3600   |83.8983     |21.5732   |28.6145     |6.04748   |
+|step 3900   |81.8544     |22.1087   |27.9359     |5.99096   |
+|step 4200   |82.9741     |23.392    |27.4288     |6.4013    |
+|step 4500   |83.8485     |24.2452   |27.0575     |6.79164   |
+|step 4800   |81.6052     |22.666    |26.6918     |6.09457   |
+|step 5100   |77.9661     |22.4803   |25.1084     |6.0098    |
+|step 5400   |77.2183     |21.83     |24.656      |5.9156    |
+|step 5700   |76.672      |22.1078   |24.2606     |6.0802    |
+|step 6000   |76.2712     |22.7589   |23.9236     |6.41485   |
+|step 6300   |75.7228     |23.8737   |23.7135     |6.78222   |
+|step 6600   |71.2363     |23.177    |22.196      |6.39601   |
+|step 6900   |69.8405     |22.7125   |21.574      |6.21703   |
+|step 7200   |72.9452     |23.6679   |21.0775     |6.6918    |
+|step 7500   |75.9222     |24.7097   |20.8999     |7.17784   |
+|step 7800   |67.4975     |23.1305   |20.6786     |6.65034   |
+|step 8100   |65.2542     |23.1305   |19.7361     |6.49962   |
+|step 8400   |61.7149     |22.3874   |18.426      |6.12283   |
+|step 8700   |63.8046     |23.6679   |18.2166     |6.2679    |
+|step 9000   |64.7059     |24.1059   |17.9952     |6.66918   |
+|step 9300   |67.5474     |24.7097   |17.6078     |7.16843   |
+|step 9600   |57.1286     |23.3163   |17.2385     |6.66918   |
+|step 9900   |58.2752     |22.8054   |17.1065     |6.4431    |
+|step 10200  |57.7767     |24.2917   |16.848      |6.68802   |
+|step 10500  |55.2841     |25.1277   |16.5033     |7.12133   |
+|step 10800  |52.5424     |23.8272   |15.9566     |6.80106   |
+|step 11100  |55.5334     |24.6168   |16.2959     |6.94235   |
+
+### Framework versions
+
+- Transformers 4.31.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.4
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,116 @@
+{
+  "_name_or_path": "ad019el/tamasheq-99-6",
+  "activation_dropout": 0.05,
+  "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": 256,
+  "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": true,
+  "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,
+  "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": 42,
+  "proj_codevector_dim": 256,
+  "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": "4.31.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 43,
+  "xvector_output_dim": 512
+}

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
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba0dd02b2e46c1cb5a1d244f1d1a10445e9a367f62825ffca69610376406b485
+size 1262078125

runs/Aug15_17-53-51_f163a2af2bd6/events.out.tfevents.1692122092.f163a2af2bd6.3941.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f7dec8c4a9d958b2b98823f254239e811b1bbd0eccb30f406f52757a7db812c
+size 7580

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 +1,13 @@
+{
+  "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": null,
+  "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:cb96442376da9c29e07c372565529befc21db5ba6630822b1a3b2ced5f51ccfb
+size 3963

vocab.json

@@ -0,0 +1,45 @@
+{
+  "[PAD]": 42,
+  "[UNK]": 41,
+  "|": 22,
+  "ء": 38,
+  "آ": 6,
+  "أ": 10,
+  "ؤ": 13,
+  "إ": 27,
+  "ئ": 12,
+  "ا": 14,
+  "ب": 18,
+  "ة": 5,
+  "ت": 26,
+  "ث": 25,
+  "ج": 35,
+  "ح": 17,
+  "خ": 28,
+  "د": 8,
+  "ذ": 21,
+  "ر": 16,
+  "ز": 29,
+  "س": 39,
+  "ش": 19,
+  "ص": 36,
+  "ض": 20,
+  "ط": 1,
+  "ظ": 37,
+  "ع": 0,
+  "غ": 33,
+  "ف": 7,
+  "ق": 15,
+  "ك": 24,
+  "ل": 11,
+  "م": 31,
+  "ن": 30,
+  "ه": 2,
+  "و": 4,
+  "ى": 23,
+  "ي": 3,
+  "ٱ": 32,
+  "ڤ": 9,
+  "ک": 40,
+  "ی": 34
+}