End of training

README.md

@@ -0,0 +1,88 @@
+---
+language:
+- ev
+license: apache-2.0
+base_model: facebook/wav2vec2-large-xlsr-53
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: wav2vec2-large-xlsr-53
+  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. -->
+
+# wav2vec2-large-xlsr-53
+
+This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the Evenki dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8728
+- Wer: 65.9678
+
+## 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: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- 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: 15
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Wer     |
+|:-------------:|:-------:|:----:|:---------------:|:-------:|
+| 8.8625        | 0.6279  | 100  | 4.7672          | 100.0   |
+| 3.5933        | 1.2559  | 200  | 3.5125          | 100.0   |
+| 3.4942        | 1.8838  | 300  | 3.4852          | 100.0   |
+| 3.5053        | 2.5118  | 400  | 3.4885          | 100.0   |
+| 3.2185        | 3.1397  | 500  | 2.8873          | 100.0   |
+| 2.2076        | 3.7677  | 600  | 1.6237          | 99.9844 |
+| 1.6129        | 4.3956  | 700  | 1.2754          | 92.5833 |
+| 1.5995        | 5.0235  | 800  | 1.1585          | 84.6033 |
+| 1.333         | 5.6515  | 900  | 1.0689          | 80.4882 |
+| 1.2571        | 6.2794  | 1000 | 1.0283          | 77.4840 |
+| 1.1675        | 6.9074  | 1100 | 0.9761          | 75.3716 |
+| 1.1193        | 7.5353  | 1200 | 0.9367          | 73.3532 |
+| 1.0054        | 8.1633  | 1300 | 0.9723          | 72.4300 |
+| 1.0211        | 8.7912  | 1400 | 0.8911          | 70.4115 |
+| 0.9408        | 9.4192  | 1500 | 0.9405          | 70.6775 |
+| 0.9115        | 10.0471 | 1600 | 0.8998          | 68.2835 |
+| 0.8533        | 10.6750 | 1700 | 0.9073          | 68.3461 |
+| 0.7981        | 11.3030 | 1800 | 0.8838          | 67.8141 |
+| 0.8154        | 11.9309 | 1900 | 0.8872          | 66.7345 |
+| 0.7603        | 12.5589 | 2000 | 0.8681          | 66.9379 |
+| 0.7711        | 13.1868 | 2100 | 0.8723          | 66.5154 |
+| 0.6974        | 13.8148 | 2200 | 0.8634          | 66.1242 |
+| 0.7224        | 14.4427 | 2300 | 0.8728          | 65.9678 |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 81,
+  "<s>": 80
+}

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": 79,
+  "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": "4.41.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 82,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c9a1df23b8684f0ec19b7642cbb954e9ca99ae420c770989bf6abb54133dd11
+size 1262143680

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
+}

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 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "78": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "79": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "80": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "81": {
+      "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]",
+  "processor_class": "Wav2Vec2Processor",
+  "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 sha256:83db0c4c2540974dc0db8b056afb9f5301e62b1150ab4518ef4651e66986f8ec
+size 5048

vocab.json

@@ -0,0 +1,82 @@
+{
+  "'": 33,
+  "[PAD]": 79,
+  "[UNK]": 78,
+  "a": 2,
+  "b": 15,
+  "d": 11,
+  "e": 32,
+  "f": 35,
+  "g": 18,
+  "h": 17,
+  "i": 4,
+  "j": 24,
+  "k": 7,
+  "l": 9,
+  "m": 12,
+  "n": 3,
+  "o": 10,
+  "p": 27,
+  "r": 8,
+  "s": 22,
+  "t": 6,
+  "u": 5,
+  "v": 43,
+  "w": 13,
+  "y": 68,
+  "z": 40,
+  "|": 0,
+  "Ø": 28,
+  "ā": 20,
+  "č": 23,
+  "ď": 19,
+  "ē": 37,
+  "ī": 16,
+  "ľ": 75,
+  "ń": 31,
+  "ŋ": 14,
+  "ō": 21,
+  "ś": 29,
+  "š": 38,
+  "ť": 46,
+  "ū": 25,
+  "ž": 39,
+  "ǝ": 67,
+  "ɔ": 73,
+  "ɕ": 71,
+  "ə": 1,
+  "ɨ": 30,
+  "ɲ": 60,
+  "ʲ": 56,
+  "̄": 26,
+  "γ": 34,
+  "а": 44,
+  "б": 58,
+  "в": 50,
+  "г": 77,
+  "д": 64,
+  "е": 47,
+  "ж": 72,
+  "з": 59,
+  "и": 48,
+  "й": 74,
+  "к": 53,
+  "л": 57,
+  "м": 55,
+  "н": 49,
+  "о": 42,
+  "п": 54,
+  "р": 45,
+  "с": 51,
+  "т": 52,
+  "у": 65,
+  "ф": 63,
+  "ч": 70,
+  "ш": 62,
+  "ы": 66,
+  "ь": 69,
+  "э": 76,
+  "я": 61,
+  "ә": 41,
+  "’": 36
+}