End of training

README.md

@@ -0,0 +1,83 @@
+---
+license: apache-2.0
+base_model: facebook/wav2vec2-large-xlsr-53
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: XLS-R_Jibbali_lang
+  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. -->
+
+# XLS-R_Jibbali_lang
+
+This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1714
+- Wer: 0.1941
+
+## 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: 0.0003
+- 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
+- num_epochs: 20
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 16.1473       | 0.99  | 56   | 11.0651         | 1.0    |
+| 3.9177        | 2.0   | 113  | 3.4720          | 1.0    |
+| 3.1902        | 2.99  | 169  | 3.1574          | 1.0    |
+| 3.1711        | 4.0   | 226  | 3.1379          | 1.0    |
+| 3.1491        | 4.99  | 282  | 3.1154          | 1.0    |
+| 3.1449        | 6.0   | 339  | 3.0533          | 1.0    |
+| 2.9214        | 6.99  | 395  | 2.7533          | 1.0    |
+| 1.9003        | 8.0   | 452  | 1.4168          | 0.9291 |
+| 0.6151        | 8.99  | 508  | 0.3110          | 0.3224 |
+| 0.2125        | 10.0  | 565  | 0.2170          | 0.2145 |
+| 0.1754        | 10.99 | 621  | 0.1987          | 0.2069 |
+| 0.1688        | 12.0  | 678  | 0.1870          | 0.1985 |
+| 0.1012        | 12.99 | 734  | 0.1856          | 0.1908 |
+| 0.1157        | 14.0  | 791  | 0.1906          | 0.2025 |
+| 0.1427        | 14.99 | 847  | 0.1844          | 0.1937 |
+| 0.0513        | 16.0  | 904  | 0.1852          | 0.1915 |
+| 0.1403        | 16.99 | 960  | 0.1713          | 0.1944 |
+| 0.1119        | 18.0  | 1017 | 0.1610          | 0.1974 |
+| 0.1034        | 18.99 | 1073 | 0.1697          | 0.1944 |
+| 0.0428        | 19.82 | 1120 | 0.1714          | 0.1941 |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,117 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "activation_dropout": 0.0,
+  "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": 768,
+  "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": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": false,
+  "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": 37,
+  "proj_codevector_dim": 768,
+  "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": "4.35.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 40,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3851d108e2cd1bfebf6683bee7d73484968f55bc1fba0598ecac36a643b35ea
+size 1261971480

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
+}

runs/Feb15_21-58-06_f87faa3d7f63/events.out.tfevents.1708034379.f87faa3d7f63.285.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc5be207ad3db5e57fe02f9aa27a40aa5180725f5b826f78471ef6139191703d
+size 30164

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a885757fbfd1eecfe55fc6924474fa7cfa4de2e3a354551aec49e2bee72af741
+size 4600