From aba429c9b8a8f872f2b3e39cf3cfe19a7f9929ae Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Fri, 16 Oct 2026 06:22:16 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: Khalsuu/filipino-wav2vec2-l-xls-r-300m-official Source: Original Platform --- .gitattributes | 27 +++++++ .gitignore | 1 + README.md | 76 ++++++++++++++++++ added_tokens.json | 1 + config.json | 79 +++++++++++++++++++ preprocessor_config.json | 10 +++ pytorch_model.bin | 3 + ....out.tfevents.1652412449.b93b174d3505.96.1 | 3 + ....out.tfevents.1652412449.b93b174d3505.96.0 | 3 + special_tokens_map.json | 1 + tokenizer_config.json | 1 + training_args.bin | 3 + vocab.json | 1 + 13 files changed, 209 insertions(+) create mode 100644 .gitattributes create mode 100644 .gitignore create mode 100644 README.md create mode 100644 added_tokens.json create mode 100644 config.json create mode 100644 preprocessor_config.json create mode 100644 pytorch_model.bin create mode 100644 runs/May13_03-26-02_b93b174d3505/1652412449.0586677/events.out.tfevents.1652412449.b93b174d3505.96.1 create mode 100644 runs/May13_03-26-02_b93b174d3505/events.out.tfevents.1652412449.b93b174d3505.96.0 create mode 100644 special_tokens_map.json create mode 100644 tokenizer_config.json create mode 100644 training_args.bin create mode 100644 vocab.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ac481c8 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,27 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..0348ea9 --- /dev/null +++ b/.gitignore @@ -0,0 +1 @@ +checkpoint-*/ \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..b9fb6d0 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +license: apache-2.0 +tags: +- generated_from_trainer +datasets: +- filipino_voice +model-index: +- name: filipino-wav2vec2-l-xls-r-300m-official + results: [] +--- + + + +# filipino-wav2vec2-l-xls-r-300m-official + +This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the filipino_voice dataset. +It achieves the following results on the evaluation set: +- Loss: 0.4672 +- Wer: 0.2922 + +## 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: 8 +- eval_batch_size: 8 +- seed: 42 +- gradient_accumulation_steps: 2 +- total_train_batch_size: 16 +- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 +- lr_scheduler_type: linear +- lr_scheduler_warmup_steps: 500 +- num_epochs: 30 +- mixed_precision_training: Native AMP + +### Training results + +| Training Loss | Epoch | Step | Validation Loss | Wer | +|:-------------:|:-----:|:----:|:---------------:|:------:| +| 3.3671 | 2.09 | 400 | 0.5584 | 0.5987 | +| 0.48 | 4.19 | 800 | 0.4244 | 0.4195 | +| 0.2796 | 6.28 | 1200 | 0.3742 | 0.3765 | +| 0.1916 | 8.38 | 1600 | 0.4291 | 0.3667 | +| 0.1463 | 10.47 | 2000 | 0.3745 | 0.3415 | +| 0.1165 | 12.57 | 2400 | 0.4472 | 0.3407 | +| 0.0955 | 14.66 | 2800 | 0.4269 | 0.3290 | +| 0.0823 | 16.75 | 3200 | 0.4608 | 0.3475 | +| 0.0709 | 18.85 | 3600 | 0.4706 | 0.3281 | +| 0.0603 | 20.94 | 4000 | 0.4380 | 0.3183 | +| 0.0527 | 23.04 | 4400 | 0.4473 | 0.3067 | +| 0.0449 | 25.13 | 4800 | 0.4550 | 0.3029 | +| 0.041 | 27.23 | 5200 | 0.4671 | 0.3020 | +| 0.0358 | 29.32 | 5600 | 0.4672 | 0.2922 | + + +### Framework versions + +- Transformers 4.11.3 +- Pytorch 1.10.0+cu113 +- Datasets 1.18.3 +- Tokenizers 0.10.3 diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..3172ba7 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1 @@ +{"": 29, "": 30} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..016e464 --- /dev/null +++ b/config.json @@ -0,0 +1,79 @@ +{ + "_name_or_path": "facebook/wav2vec2-xls-r-300m", + "activation_dropout": 0.0, + "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, + "gradient_checkpointing": false, + "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_feature_length": 10, + "mask_feature_prob": 0.0, + "mask_time_length": 10, + "mask_time_prob": 0.05, + "model_type": "wav2vec2", + "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, + "pad_token_id": 28, + "proj_codevector_dim": 768, + "torch_dtype": "float32", + "transformers_version": "4.11.3", + "use_weighted_layer_sum": false, + "vocab_size": 31 +} diff --git a/preprocessor_config.json b/preprocessor_config.json new file mode 100644 index 0000000..7cd4b93 --- /dev/null +++ b/preprocessor_config.json @@ -0,0 +1,10 @@ +{ + "do_normalize": true, + "feature_extractor_type": "Wav2Vec2FeatureExtractor", + "feature_size": 1, + "padding_side": "right", + "padding_value": 0.0, + "return_attention_mask": true, + "return_tensors": "np", + "sampling_rate": 16000 +} diff --git a/pytorch_model.bin b/pytorch_model.bin new file mode 100644 index 0000000..eeb81b7 --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20d9bde03634fa29feec409abc66ba0df3e3b4450f5bbba202c49c65cabe030c +size 1262050737 diff --git a/runs/May13_03-26-02_b93b174d3505/1652412449.0586677/events.out.tfevents.1652412449.b93b174d3505.96.1 b/runs/May13_03-26-02_b93b174d3505/1652412449.0586677/events.out.tfevents.1652412449.b93b174d3505.96.1 new file mode 100644 index 0000000..6f66dd3 --- /dev/null +++ b/runs/May13_03-26-02_b93b174d3505/1652412449.0586677/events.out.tfevents.1652412449.b93b174d3505.96.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a6d70dfa4e4c6dc0bf56bcc80330baa3613784384d8b595ddd2bf096dd5b8cc +size 4582 diff --git a/runs/May13_03-26-02_b93b174d3505/events.out.tfevents.1652412449.b93b174d3505.96.0 b/runs/May13_03-26-02_b93b174d3505/events.out.tfevents.1652412449.b93b174d3505.96.0 new file mode 100644 index 0000000..cf99d14 --- /dev/null +++ b/runs/May13_03-26-02_b93b174d3505/events.out.tfevents.1652412449.b93b174d3505.96.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a21f081ee775c3573da85f4c2513b695840f02e723c525e8a2ced8a84015535 +size 11240 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..623bcb0 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1 @@ +{"bos_token": "", "eos_token": "", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]} \ No newline at end of file diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..29fcea5 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1 @@ +{"unk_token": "[UNK]", "bos_token": "", "eos_token": "", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"} \ No newline at end of file diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..dbaa979 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26195e48d53e13187697974d42f1ca07b151dfc1774f2cb8d03c5662c874dc3e +size 2863 diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..1e1cd78 --- /dev/null +++ b/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, "|": 0, "[UNK]": 27, "[PAD]": 28} \ No newline at end of file