base model

README.md

@@ -0,0 +1,98 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+- "es"
+- "robust-speech-event"
+datasets:
+- common_voice
+model-index:
+- name: wav2vec2-large-xls-r-300m-spanish-large
+  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-xls-r-300m-spanish-large
+
+This model is a fine-tuned version of [tomascufaro/xls-r-es-test](https://huggingface.co/tomascufaro/xls-r-es-test) on the common_voice dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1431
+- Wer: 0.1197
+
+## 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: 0.0002
+- train_batch_size: 10
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 20
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 300
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Wer    |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|
+| 0.1769        | 0.15  | 400   | 0.1795          | 0.1698 |
+| 0.217         | 0.3   | 800   | 0.2000          | 0.1945 |
+| 0.2372        | 0.45  | 1200  | 0.1985          | 0.1859 |
+| 0.2351        | 0.6   | 1600  | 0.1901          | 0.1772 |
+| 0.2269        | 0.75  | 2000  | 0.1968          | 0.1783 |
+| 0.2284        | 0.9   | 2400  | 0.1873          | 0.1771 |
+| 0.2014        | 1.06  | 2800  | 0.1840          | 0.1696 |
+| 0.1988        | 1.21  | 3200  | 0.1904          | 0.1730 |
+| 0.1919        | 1.36  | 3600  | 0.1827          | 0.1630 |
+| 0.1919        | 1.51  | 4000  | 0.1788          | 0.1629 |
+| 0.1817        | 1.66  | 4400  | 0.1755          | 0.1558 |
+| 0.1812        | 1.81  | 4800  | 0.1795          | 0.1638 |
+| 0.1808        | 1.96  | 5200  | 0.1762          | 0.1603 |
+| 0.1625        | 2.11  | 5600  | 0.1721          | 0.1557 |
+| 0.1477        | 2.26  | 6000  | 0.1735          | 0.1504 |
+| 0.1508        | 2.41  | 6400  | 0.1708          | 0.1478 |
+| 0.157         | 2.56  | 6800  | 0.1644          | 0.1466 |
+| 0.1491        | 2.71  | 7200  | 0.1638          | 0.1445 |
+| 0.1458        | 2.86  | 7600  | 0.1582          | 0.1426 |
+| 0.1387        | 3.02  | 8000  | 0.1607          | 0.1376 |
+| 0.1269        | 3.17  | 8400  | 0.1559          | 0.1364 |
+| 0.1172        | 3.32  | 8800  | 0.1521          | 0.1335 |
+| 0.1203        | 3.47  | 9200  | 0.1534          | 0.1330 |
+| 0.1177        | 3.62  | 9600  | 0.1485          | 0.1304 |
+| 0.1167        | 3.77  | 10000 | 0.1498          | 0.1302 |
+| 0.1194        | 3.92  | 10400 | 0.1463          | 0.1287 |
+| 0.1053        | 4.07  | 10800 | 0.1483          | 0.1282 |
+| 0.098         | 4.22  | 11200 | 0.1498          | 0.1267 |
+| 0.0958        | 4.37  | 11600 | 0.1461          | 0.1233 |
+| 0.0946        | 4.52  | 12000 | 0.1444          | 0.1218 |
+| 0.094         | 4.67  | 12400 | 0.1434          | 0.1206 |
+| 0.0932        | 4.82  | 12800 | 0.1424          | 0.1206 |
+| 0.0912        | 4.98  | 13200 | 0.1431          | 0.1197 |
+
+
+### Framework versions
+
+- Transformers 4.17.0.dev0
+- Pytorch 1.10.2+cu102
+- Datasets 1.18.2.dev0
+- Tokenizers 0.11.0

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 34, "</s>": 35}

config.json

@@ -0,0 +1,115 @@
+{
+  "_name_or_path": "tomascufaro/xls-r-es-test",
+  "activation_dropout": 0.1,
+  "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": 64,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.25,
+  "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": 33,
+  "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": "4.17.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 36,
+  "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 sha256:3c41222f5493b1c33722cc54f4187750cebfd7d194b2f6ffc95a261b99f8dfb0
+size 1262071281

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:746ee9d68c06fa57de985af684a3a28c5f379833673e91d135b889b6bed394cd
+size 3055

vocab.json

@@ -0,0 +1 @@
+{"a": 1, "b": 2, "c": 3, "d": 4, "e": 5, "f": 6, "g": 7, "h": 8, "i": 9, "j": 10, "k": 11, "l": 12, "m": 13, "n": 14, "o": 15, "p": 16, "q": 17, "r": 18, "s": 19, "t": 20, "u": 21, "v": 22, "w": 23, "x": 24, "y": 25, "z": 26, "á": 27, "í": 28, "ñ": 29, "ó": 30, "ú": 31, "|": 0, "[UNK]": 32, "[PAD]": 33}