Add/Update model artifacts

agent/acoustic/acoustic_scaler.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a293589603ee75ad1b4d3c522db0eadc8536bd22d8c1cdb58e96ec6400523a65
+size 1527

agent/acoustic/randomforest_acoustic_model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82c81d3adaaa40046c9402898bc7f675b90b5f0d02cf655817af0acb20efbc33
+size 5724433

agent/acoustic/svm_acoustic_model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3e0e7f53578abfb47d8babf69ed7cc831a5a0b7208a51014052dbdec07dbb27
+size 579555

agent/text/best_model/config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "SI2M-Lab/DarijaBERT",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "aggressive",
+    "1": "courtois",
+    "2": "sec"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "aggressive": 0,
+    "courtois": 1,
+    "sec": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "mask_token": "[MASK]",
+  "max_len": 128,
+  "max_position_embeddings": 512,
+  "model_max_length": 128,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token": "[PAD]",
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "sep_token": "[SEP]",
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.3",
+  "type_vocab_size": 2,
+  "unk_token": "[UNK]",
+  "use_cache": true,
+  "vocab_size": 80000
+}

agent/text/best_model/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b07682e083d17d041bdbc77bdc19a2ae576eaf349fdc58cf7e30820818096ec
+size 590003438

agent/text/best_model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebc421668ec59fcd0f8e105fe824fa99e64cae00e5192669714e2a6da8bbbba0
+size 5368

client/acoustic/acoustic_scaler.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:161d0c8cdcfdc7c3fc229606cabadb0c75c7e446a5b4a77cf1dab7d4253c579b
+size 1527

client/acoustic/randomforest_acoustic_model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18fab4d53235941d54e10742717be6c151a2232d207a2b2b10bb670c4380a7a4
+size 4156625

client/acoustic/svm_acoustic_model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aa4d84363bd11e7a8c321677e404a637ce6c321e2d0ea40b39a0f0dc7bb7066
+size 437459

client/text/best_model/config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "SI2M-Lab/DarijaBERT",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "content",
+    "1": "neutre",
+    "2": "tres mecontent"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "content": 0,
+    "neutre": 1,
+    "tres mecontent": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "mask_token": "[MASK]",
+  "max_len": 128,
+  "max_position_embeddings": 512,
+  "model_max_length": 128,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token": "[PAD]",
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "sep_token": "[SEP]",
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.3",
+  "type_vocab_size": 2,
+  "unk_token": "[UNK]",
+  "use_cache": true,
+  "vocab_size": 80000
+}

client/text/best_model/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a97f23ea9c953d26eb314bbcf11ab292eaef85577353e4f71358ffdcd79b2929
+size 590003438

client/text/best_model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf2a6b9904c864e3fb34ed5b56de4cc2aa5627737d86fe02bb78a4067e59fe5c
+size 5368

transcription/w2v-bert-darija-finetuned-clean/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 57,
+  "<s>": 56
+}

transcription/w2v-bert-darija-finetuned-clean/checkpoint-1490/config.json

@@ -0,0 +1,82 @@
+{
+  "_name_or_path": "facebook/w2v-bert-2.0",
+  "activation_dropout": 0.0,
+  "adapter_act": "relu",
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": true,
+  "apply_spec_augment": false,
+  "architectures": [
+    "Wav2Vec2BertForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 768,
+  "codevector_dim": 768,
+  "conformer_conv_dropout": 0.1,
+  "contrastive_logits_temperature": 0.1,
+  "conv_depthwise_kernel_size": 31,
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "eos_token_id": 2,
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "feature_projection_input_dim": 160,
+  "final_dropout": 0.1,
+  "hidden_act": "swish",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "left_max_position_embeddings": 64,
+  "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": 0.0,
+  "max_source_positions": 5000,
+  "model_type": "wav2vec2-bert",
+  "num_adapter_layers": 1,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 55,
+  "position_embeddings_type": "relative_key",
+  "proj_codevector_dim": 768,
+  "right_max_position_embeddings": 8,
+  "rotary_embedding_base": 10000,
+  "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": "4.46.3",
+  "use_intermediate_ffn_before_adapter": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 58,
+  "xvector_output_dim": 512
+}

transcription/w2v-bert-darija-finetuned-clean/checkpoint-1490/preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "feature_extractor_type": "SeamlessM4TFeatureExtractor",
+  "feature_size": 80,
+  "num_mel_bins": 80,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "stride": 2
+}

transcription/w2v-bert-darija-finetuned-clean/checkpoint-1490/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2a812a278c72cb787298245f122ab589285b867cb9fb13812819e443341549a
+size 14244

transcription/w2v-bert-darija-finetuned-clean/checkpoint-1490/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a83b4666c22523603f0a60b34d13d8692110ae1c6107f863de3447d27acb008b
+size 1064

transcription/w2v-bert-darija-finetuned-clean/checkpoint-1490/trainer_state.json

@@ -0,0 +1,220 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.99630996309963,
+  "eval_steps": 500,
+  "global_step": 1490,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.996309963099631,
+      "grad_norm": 6.060778617858887,
+      "learning_rate": 1.3100000000000002e-05,
+      "loss": 4.0745,
+      "step": 135
+    },
+    {
+      "epoch": 0.996309963099631,
+      "eval_loss": 2.8919060230255127,
+      "eval_pen_wer": 0.9288469971028115,
+      "eval_runtime": 35.4574,
+      "eval_samples_per_second": 7.643,
+      "eval_steps_per_second": 0.959,
+      "eval_wer": 0.9983822042467139,
+      "step": 135
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 32.26631164550781,
+      "learning_rate": 2.6700000000000002e-05,
+      "loss": 1.9077,
+      "step": 271
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.279911756515503,
+      "eval_pen_wer": 0.4244393978114909,
+      "eval_runtime": 36.3495,
+      "eval_samples_per_second": 7.455,
+      "eval_steps_per_second": 0.935,
+      "eval_wer": 0.6604651162790698,
+      "step": 271
+    },
+    {
+      "epoch": 2.9963099630996313,
+      "grad_norm": 5.846123218536377,
+      "learning_rate": 4.02e-05,
+      "loss": 1.2007,
+      "step": 406
+    },
+    {
+      "epoch": 2.9963099630996313,
+      "eval_loss": 1.1114612817764282,
+      "eval_pen_wer": 0.36216589798996246,
+      "eval_runtime": 36.7217,
+      "eval_samples_per_second": 7.38,
+      "eval_steps_per_second": 0.926,
+      "eval_wer": 0.5937984496124031,
+      "step": 406
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 7.9398193359375,
+      "learning_rate": 4.8303571428571434e-05,
+      "loss": 1.0249,
+      "step": 542
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.0737940073013306,
+      "eval_pen_wer": 0.34027092257628144,
+      "eval_runtime": 36.6597,
+      "eval_samples_per_second": 7.392,
+      "eval_steps_per_second": 0.927,
+      "eval_wer": 0.5542298618132794,
+      "step": 542
+    },
+    {
+      "epoch": 4.996309963099631,
+      "grad_norm": 5.927522659301758,
+      "learning_rate": 4.2276785714285714e-05,
+      "loss": 0.8813,
+      "step": 677
+    },
+    {
+      "epoch": 4.996309963099631,
+      "eval_loss": 1.0277714729309082,
+      "eval_pen_wer": 0.34514653099587383,
+      "eval_runtime": 36.4973,
+      "eval_samples_per_second": 7.425,
+      "eval_steps_per_second": 0.932,
+      "eval_wer": 0.5530165149983148,
+      "step": 677
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 11.025650978088379,
+      "learning_rate": 3.620535714285714e-05,
+      "loss": 0.7769,
+      "step": 813
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.9775798320770264,
+      "eval_pen_wer": 0.32710190850231297,
+      "eval_runtime": 36.7174,
+      "eval_samples_per_second": 7.381,
+      "eval_steps_per_second": 0.926,
+      "eval_wer": 0.5332659251769464,
+      "step": 813
+    },
+    {
+      "epoch": 6.996309963099631,
+      "grad_norm": 6.112392425537109,
+      "learning_rate": 3.0178571428571427e-05,
+      "loss": 0.7,
+      "step": 948
+    },
+    {
+      "epoch": 6.996309963099631,
+      "eval_loss": 0.9915932416915894,
+      "eval_pen_wer": 0.3124926266483397,
+      "eval_runtime": 36.3976,
+      "eval_samples_per_second": 7.446,
+      "eval_steps_per_second": 0.934,
+      "eval_wer": 0.5078530502190766,
+      "step": 948
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 17.379560470581055,
+      "learning_rate": 2.4107142857142858e-05,
+      "loss": 0.6065,
+      "step": 1084
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.992123544216156,
+      "eval_pen_wer": 0.31970698851386425,
+      "eval_runtime": 36.1353,
+      "eval_samples_per_second": 7.5,
+      "eval_steps_per_second": 0.941,
+      "eval_wer": 0.5029322548028311,
+      "step": 1084
+    },
+    {
+      "epoch": 8.99630996309963,
+      "grad_norm": 7.368852615356445,
+      "learning_rate": 1.8080357142857144e-05,
+      "loss": 0.5375,
+      "step": 1219
+    },
+    {
+      "epoch": 8.99630996309963,
+      "eval_loss": 0.984150230884552,
+      "eval_pen_wer": 0.302135588075932,
+      "eval_runtime": 36.9038,
+      "eval_samples_per_second": 7.343,
+      "eval_steps_per_second": 0.921,
+      "eval_wer": 0.4912032355915066,
+      "step": 1219
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 9.9882230758667,
+      "learning_rate": 1.2008928571428573e-05,
+      "loss": 0.4681,
+      "step": 1355
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.0245816707611084,
+      "eval_pen_wer": 0.3019771813401745,
+      "eval_runtime": 36.9691,
+      "eval_samples_per_second": 7.33,
+      "eval_steps_per_second": 0.92,
+      "eval_wer": 0.4895180316818335,
+      "step": 1355
+    },
+    {
+      "epoch": 10.99630996309963,
+      "grad_norm": 5.356689453125,
+      "learning_rate": 5.982142857142858e-06,
+      "loss": 0.415,
+      "step": 1490
+    },
+    {
+      "epoch": 10.99630996309963,
+      "eval_loss": 1.0347157716751099,
+      "eval_pen_wer": 0.29928239999524137,
+      "eval_runtime": 36.6987,
+      "eval_samples_per_second": 7.384,
+      "eval_steps_per_second": 0.926,
+      "eval_wer": 0.48230535894843274,
+      "step": 1490
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1620,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 12,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.432449882085846e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

transcription/w2v-bert-darija-finetuned-clean/checkpoint-1490/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2793aaf5af1a42cb015bfef656c097f2acac87a48fffa9d3175eaeceb802e54
+size 5304

transcription/w2v-bert-darija-finetuned-clean/checkpoint-1620/config.json

@@ -0,0 +1,82 @@
+{
+  "_name_or_path": "facebook/w2v-bert-2.0",
+  "activation_dropout": 0.0,
+  "adapter_act": "relu",
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": true,
+  "apply_spec_augment": false,
+  "architectures": [
+    "Wav2Vec2BertForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 768,
+  "codevector_dim": 768,
+  "conformer_conv_dropout": 0.1,
+  "contrastive_logits_temperature": 0.1,
+  "conv_depthwise_kernel_size": 31,
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "eos_token_id": 2,
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "feature_projection_input_dim": 160,
+  "final_dropout": 0.1,
+  "hidden_act": "swish",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "left_max_position_embeddings": 64,
+  "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": 0.0,
+  "max_source_positions": 5000,
+  "model_type": "wav2vec2-bert",
+  "num_adapter_layers": 1,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 55,
+  "position_embeddings_type": "relative_key",
+  "proj_codevector_dim": 768,
+  "right_max_position_embeddings": 8,
+  "rotary_embedding_base": 10000,
+  "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": "4.46.3",
+  "use_intermediate_ffn_before_adapter": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 58,
+  "xvector_output_dim": 512
+}

transcription/w2v-bert-darija-finetuned-clean/checkpoint-1620/preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "feature_extractor_type": "SeamlessM4TFeatureExtractor",
+  "feature_size": 80,
+  "num_mel_bins": 80,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "stride": 2
+}

transcription/w2v-bert-darija-finetuned-clean/checkpoint-1620/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a995beb400c6c1030bc370a69431ecc53b71182f594e2d6947b1b9a8e2bf06a7
+size 14244

transcription/w2v-bert-darija-finetuned-clean/checkpoint-1620/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8678820546c1a63031103789e84d8dddaf3251d385b714efbe8413d1d83de7f5
+size 1064

transcription/w2v-bert-darija-finetuned-clean/checkpoint-1620/trainer_state.json

@@ -0,0 +1,237 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 11.955719557195572,
+  "eval_steps": 500,
+  "global_step": 1620,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.996309963099631,
+      "grad_norm": 6.060778617858887,
+      "learning_rate": 1.3100000000000002e-05,
+      "loss": 4.0745,
+      "step": 135
+    },
+    {
+      "epoch": 0.996309963099631,
+      "eval_loss": 2.8919060230255127,
+      "eval_pen_wer": 0.9288469971028115,
+      "eval_runtime": 35.4574,
+      "eval_samples_per_second": 7.643,
+      "eval_steps_per_second": 0.959,
+      "eval_wer": 0.9983822042467139,
+      "step": 135
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 32.26631164550781,
+      "learning_rate": 2.6700000000000002e-05,
+      "loss": 1.9077,
+      "step": 271
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.279911756515503,
+      "eval_pen_wer": 0.4244393978114909,
+      "eval_runtime": 36.3495,
+      "eval_samples_per_second": 7.455,
+      "eval_steps_per_second": 0.935,
+      "eval_wer": 0.6604651162790698,
+      "step": 271
+    },
+    {
+      "epoch": 2.9963099630996313,
+      "grad_norm": 5.846123218536377,
+      "learning_rate": 4.02e-05,
+      "loss": 1.2007,
+      "step": 406
+    },
+    {
+      "epoch": 2.9963099630996313,
+      "eval_loss": 1.1114612817764282,
+      "eval_pen_wer": 0.36216589798996246,
+      "eval_runtime": 36.7217,
+      "eval_samples_per_second": 7.38,
+      "eval_steps_per_second": 0.926,
+      "eval_wer": 0.5937984496124031,
+      "step": 406
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 7.9398193359375,
+      "learning_rate": 4.8303571428571434e-05,
+      "loss": 1.0249,
+      "step": 542
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.0737940073013306,
+      "eval_pen_wer": 0.34027092257628144,
+      "eval_runtime": 36.6597,
+      "eval_samples_per_second": 7.392,
+      "eval_steps_per_second": 0.927,
+      "eval_wer": 0.5542298618132794,
+      "step": 542
+    },
+    {
+      "epoch": 4.996309963099631,
+      "grad_norm": 5.927522659301758,
+      "learning_rate": 4.2276785714285714e-05,
+      "loss": 0.8813,
+      "step": 677
+    },
+    {
+      "epoch": 4.996309963099631,
+      "eval_loss": 1.0277714729309082,
+      "eval_pen_wer": 0.34514653099587383,
+      "eval_runtime": 36.4973,
+      "eval_samples_per_second": 7.425,
+      "eval_steps_per_second": 0.932,
+      "eval_wer": 0.5530165149983148,
+      "step": 677
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 11.025650978088379,
+      "learning_rate": 3.620535714285714e-05,
+      "loss": 0.7769,
+      "step": 813
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.9775798320770264,
+      "eval_pen_wer": 0.32710190850231297,
+      "eval_runtime": 36.7174,
+      "eval_samples_per_second": 7.381,
+      "eval_steps_per_second": 0.926,
+      "eval_wer": 0.5332659251769464,
+      "step": 813
+    },
+    {
+      "epoch": 6.996309963099631,
+      "grad_norm": 6.112392425537109,
+      "learning_rate": 3.0178571428571427e-05,
+      "loss": 0.7,
+      "step": 948
+    },
+    {
+      "epoch": 6.996309963099631,
+      "eval_loss": 0.9915932416915894,
+      "eval_pen_wer": 0.3124926266483397,
+      "eval_runtime": 36.3976,
+      "eval_samples_per_second": 7.446,
+      "eval_steps_per_second": 0.934,
+      "eval_wer": 0.5078530502190766,
+      "step": 948
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 17.379560470581055,
+      "learning_rate": 2.4107142857142858e-05,
+      "loss": 0.6065,
+      "step": 1084
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.992123544216156,
+      "eval_pen_wer": 0.31970698851386425,
+      "eval_runtime": 36.1353,
+      "eval_samples_per_second": 7.5,
+      "eval_steps_per_second": 0.941,
+      "eval_wer": 0.5029322548028311,
+      "step": 1084
+    },
+    {
+      "epoch": 8.99630996309963,
+      "grad_norm": 7.368852615356445,
+      "learning_rate": 1.8080357142857144e-05,
+      "loss": 0.5375,
+      "step": 1219
+    },
+    {
+      "epoch": 8.99630996309963,
+      "eval_loss": 0.984150230884552,
+      "eval_pen_wer": 0.302135588075932,
+      "eval_runtime": 36.9038,
+      "eval_samples_per_second": 7.343,
+      "eval_steps_per_second": 0.921,
+      "eval_wer": 0.4912032355915066,
+      "step": 1219
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 9.9882230758667,
+      "learning_rate": 1.2008928571428573e-05,
+      "loss": 0.4681,
+      "step": 1355
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.0245816707611084,
+      "eval_pen_wer": 0.3019771813401745,
+      "eval_runtime": 36.9691,
+      "eval_samples_per_second": 7.33,
+      "eval_steps_per_second": 0.92,
+      "eval_wer": 0.4895180316818335,
+      "step": 1355
+    },
+    {
+      "epoch": 10.99630996309963,
+      "grad_norm": 5.356689453125,
+      "learning_rate": 5.982142857142858e-06,
+      "loss": 0.415,
+      "step": 1490
+    },
+    {
+      "epoch": 10.99630996309963,
+      "eval_loss": 1.0347157716751099,
+      "eval_pen_wer": 0.29928239999524137,
+      "eval_runtime": 36.6987,
+      "eval_samples_per_second": 7.384,
+      "eval_steps_per_second": 0.926,
+      "eval_wer": 0.48230535894843274,
+      "step": 1490
+    },
+    {
+      "epoch": 11.955719557195572,
+      "grad_norm": 6.189606666564941,
+      "learning_rate": 1.7857142857142858e-07,
+      "loss": 0.3668,
+      "step": 1620
+    },
+    {
+      "epoch": 11.955719557195572,
+      "eval_loss": 1.0610431432724,
+      "eval_pen_wer": 0.2970119003941046,
+      "eval_runtime": 36.7697,
+      "eval_samples_per_second": 7.37,
+      "eval_steps_per_second": 0.925,
+      "eval_wer": 0.4813616447590158,
+      "step": 1620
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1620,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 12,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.176643836587086e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

transcription/w2v-bert-darija-finetuned-clean/checkpoint-1620/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2793aaf5af1a42cb015bfef656c097f2acac87a48fffa9d3175eaeceb802e54
+size 5304

transcription/w2v-bert-darija-finetuned-clean/config.json

@@ -0,0 +1,82 @@
+{
+  "_name_or_path": "facebook/w2v-bert-2.0",
+  "activation_dropout": 0.0,
+  "adapter_act": "relu",
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": true,
+  "apply_spec_augment": false,
+  "architectures": [
+    "Wav2Vec2BertForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 768,
+  "codevector_dim": 768,
+  "conformer_conv_dropout": 0.1,
+  "contrastive_logits_temperature": 0.1,
+  "conv_depthwise_kernel_size": 31,
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "eos_token_id": 2,
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "feature_projection_input_dim": 160,
+  "final_dropout": 0.1,
+  "hidden_act": "swish",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "left_max_position_embeddings": 64,
+  "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": 0.0,
+  "max_source_positions": 5000,
+  "model_type": "wav2vec2-bert",
+  "num_adapter_layers": 1,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 55,
+  "position_embeddings_type": "relative_key",
+  "proj_codevector_dim": 768,
+  "right_max_position_embeddings": 8,
+  "rotary_embedding_base": 10000,
+  "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": "4.46.3",
+  "use_intermediate_ffn_before_adapter": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 58,
+  "xvector_output_dim": 512
+}

transcription/w2v-bert-darija-finetuned-clean/preprocessor_config.json

@@ -0,0 +1,11 @@
+{
+  "feature_extractor_type": "SeamlessM4TFeatureExtractor",
+  "feature_size": 80,
+  "num_mel_bins": 80,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2BertProcessor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "stride": 2
+}

transcription/w2v-bert-darija-finetuned-clean/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

transcription/w2v-bert-darija-finetuned-clean/tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "54": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "55": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "56": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57": {
+      "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>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2BertProcessor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

transcription/w2v-bert-darija-finetuned-clean/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2793aaf5af1a42cb015bfef656c097f2acac87a48fffa9d3175eaeceb802e54
+size 5304

transcription/w2v-bert-darija-finetuned-clean/vocab.json

@@ -0,0 +1,58 @@
+{
+  "\t": 0,
+  "\n": 1,
+  "!": 3,
+  "(": 4,
+  ")": 5,
+  ",": 6,
+  ".": 7,
+  "?": 8,
+  "[PAD]": 55,
+  "[UNK]": 54,
+  "|": 2,
+  "،": 9,
+  "؟": 10,
+  "ء": 11,
+  "آ": 12,
+  "أ": 13,
+  "ؤ": 14,
+  "إ": 15,
+  "ئ": 16,
+  "ا": 17,
+  "ب": 18,
+  "ة": 19,
+  "ت": 20,
+  "ث": 21,
+  "ج": 22,
+  "ح": 23,
+  "خ": 24,
+  "د": 25,
+  "ذ": 26,
+  "ر": 27,
+  "ز": 28,
+  "س": 29,
+  "ش": 30,
+  "ص": 31,
+  "ض": 32,
+  "ط": 33,
+  "ظ": 34,
+  "ع": 35,
+  "غ": 36,
+  "ف": 37,
+  "ق": 38,
+  "ك": 39,
+  "ل": 40,
+  "م": 41,
+  "ن": 42,
+  "ه": 43,
+  "و": 44,
+  "ى": 45,
+  "ي": 46,
+  "ً": 47,
+  "ٍ": 48,
+  "ّ": 49,
+  "ٱ": 50,
+  "پ": 51,
+  "ڤ": 52,
+  "ڭ": 53
+}