Training in progress, step 500

README.md

@@ -0,0 +1,84 @@
+---
+license: apache-2.0
+base_model: facebook/wav2vec2-large-xlsr-53
+tags:
+- automatic-speech-recognition
+- techiaith/banc-trawsgrifiadau-bangor
+- generated_from_trainer
+datasets:
+- banc-trawsgrifiadau-bangor
+metrics:
+- wer
+model-index:
+- name: wav2vec2-xlsr-53-ft-btb-cy
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: TECHIAITH/BANC-TRAWSGRIFIADAU-BANGOR - CY
+      type: banc-trawsgrifiadau-bangor
+      config: cy
+      split: test
+      args: 'Config: cy, Training split: train, Eval split: test'
+    metrics:
+    - name: Wer
+      type: wer
+      value: 0.44248649327805
+---
+
+<!-- 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-xlsr-53-ft-btb-cy
+
+This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the TECHIAITH/BANC-TRAWSGRIFIADAU-BANGOR - CY dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5992
+- Wer: 0.4425
+
+## 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: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 800
+- training_steps: 5000
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 4.6574        | 1.41  | 500  | 1.0889          | 0.7293 |
+| 1.0887        | 2.83  | 1000 | 0.5992          | 0.4425 |
+| 0.7223        | 4.24  | 1500 | 0.7267          | 0.4631 |
+| 2.1295        | 5.66  | 2000 | 3.0492          | 0.9984 |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.1+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.0

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 52,
+  "<s>": 51
+}

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 5.66,
+    "eval_loss": 0.5991869568824768,
+    "eval_runtime": 213.631,
+    "eval_samples": 5656,
+    "eval_samples_per_second": 26.476,
+    "eval_steps_per_second": 0.829,
+    "eval_wer": 0.44248649327805,
+    "train_loss": 1.8628226623535156,
+    "train_runtime": 6582.3574,
+    "train_samples": 22621,
+    "train_samples_per_second": 48.615,
+    "train_steps_per_second": 0.76
+}

config.json

@@ -0,0 +1,116 @@
+{
+  "_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": 0.0,
+  "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,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "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": 50,
+  "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": "4.40.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 53,
+  "xvector_output_dim": 512
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.66,
+    "eval_loss": 0.5991869568824768,
+    "eval_runtime": 213.631,
+    "eval_samples": 5656,
+    "eval_samples_per_second": 26.476,
+    "eval_steps_per_second": 0.829,
+    "eval_wer": 0.44248649327805
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c793a579aa1465e577413ca9c6efa256442715c012e2fd3f66b7f753f2821598
+size 1262024780

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
+}

runs/May10_07-12-18_98ffe85cdad5/events.out.tfevents.1715322135.98ffe85cdad5.29.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9957da7384dd8db295c4d33764cef8e719dc9673f6a9dc70783f94a128041d97
+size 6436

runs/May10_07-37-48_617ab803152d/events.out.tfevents.1715323079.617ab803152d.31.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aac08b54ed83ac276d462939d0fead883a576e2ceb215f5f786ae3ee456f0d9c
+size 6436

runs/May10_07-39-17_6b3e2401f443/events.out.tfevents.1715323166.6b3e2401f443.30.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb227836f642ba813cdfb5ee10d07ab35132c8cb967b67b28d9e24d222418897
+size 6965

runs/Nov23_07-55-30_d403632c4022/events.out.tfevents.1700726396.d403632c4022.1864.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:854013c54e1875ae9900dfa4d32c0306c2a74404ec9bc38e7e3d20f03c3f7502
+size 8387

runs/Nov23_07-55-30_d403632c4022/events.out.tfevents.1700733346.d403632c4022.1864.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd66ec1aeb90159573d9a7bbee2d957b8bfffbcb0e39cea89072d29383f0ca83
+size 406

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "49": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "52": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "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": "|"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.66,
+    "train_loss": 1.8628226623535156,
+    "train_runtime": 6582.3574,
+    "train_samples": 22621,
+    "train_samples_per_second": 48.615,
+    "train_steps_per_second": 0.76
+}

trainer_state.json

@@ -0,0 +1,94 @@
+{
+  "best_metric": 0.5991869568824768,
+  "best_model_checkpoint": "/models/hfhub/DewiBrynJones/wav2vec2-xlsr-53-ft-btb-cy/checkpoint-1000",
+  "epoch": 5.657708628005658,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00014812499999999998,
+      "loss": 4.6574,
+      "step": 400
+    },
+    {
+      "epoch": 1.41,
+      "eval_loss": 1.0889060497283936,
+      "eval_runtime": 233.5812,
+      "eval_samples_per_second": 24.214,
+      "eval_steps_per_second": 0.758,
+      "eval_wer": 0.7293001633371027,
+      "step": 500
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 0.00029662499999999996,
+      "loss": 1.0887,
+      "step": 800
+    },
+    {
+      "epoch": 2.83,
+      "eval_loss": 0.5991869568824768,
+      "eval_runtime": 234.4544,
+      "eval_samples_per_second": 24.124,
+      "eval_steps_per_second": 0.755,
+      "eval_wer": 0.44248649327805,
+      "step": 1000
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 0.0002722142857142857,
+      "loss": 0.7223,
+      "step": 1200
+    },
+    {
+      "epoch": 4.24,
+      "eval_loss": 0.726735532283783,
+      "eval_runtime": 213.9298,
+      "eval_samples_per_second": 26.439,
+      "eval_steps_per_second": 0.827,
+      "eval_wer": 0.46312350797838925,
+      "step": 1500
+    },
+    {
+      "epoch": 4.53,
+      "learning_rate": 0.0002439285714285714,
+      "loss": 0.7162,
+      "step": 1600
+    },
+    {
+      "epoch": 5.66,
+      "learning_rate": 0.00021564285714285712,
+      "loss": 2.1295,
+      "step": 2000
+    },
+    {
+      "epoch": 5.66,
+      "eval_loss": 3.0491700172424316,
+      "eval_runtime": 217.4025,
+      "eval_samples_per_second": 26.016,
+      "eval_steps_per_second": 0.814,
+      "eval_wer": 0.9983980399547682,
+      "step": 2000
+    },
+    {
+      "epoch": 5.66,
+      "step": 2000,
+      "total_flos": 1.5333464503060175e+19,
+      "train_loss": 1.8628226623535156,
+      "train_runtime": 6582.3574,
+      "train_samples_per_second": 48.615,
+      "train_steps_per_second": 0.76
+    }
+  ],
+  "logging_steps": 400,
+  "max_steps": 5000,
+  "num_train_epochs": 15,
+  "save_steps": 500,
+  "total_flos": 1.5333464503060175e+19,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11db91cc3e5d1dc8b26dae3f198d038e603fc93e95040bd002af19679206ad3b
+size 5048

vocab.json

@@ -0,0 +1,53 @@
+{
+  "#": 1,
+  "'": 2,
+  "-": 3,
+  "@": 4,
+  "[PAD]": 50,
+  "[UNK]": 49,
+  "a": 5,
+  "b": 6,
+  "c": 7,
+  "d": 8,
+  "e": 9,
+  "f": 10,
+  "g": 11,
+  "h": 12,
+  "i": 13,
+  "j": 14,
+  "k": 15,
+  "l": 16,
+  "m": 17,
+  "n": 18,
+  "o": 19,
+  "p": 20,
+  "q": 21,
+  "r": 22,
+  "s": 23,
+  "t": 24,
+  "u": 25,
+  "v": 26,
+  "w": 27,
+  "x": 28,
+  "y": 29,
+  "z": 30,
+  "|": 0,
+  "~": 31,
+  "á": 32,
+  "â": 33,
+  "è": 34,
+  "é": 35,
+  "ê": 36,
+  "î": 37,
+  "ï": 38,
+  "ó": 39,
+  "ô": 40,
+  "ö": 41,
+  "û": 42,
+  "ü": 43,
+  "č": 44,
+  "ł": 45,
+  "ŵ": 46,
+  "ŷ": 47,
+  "ž": 48
+}