Upload 9 files

README.md

@@ -1,3 +1,82 @@
 ---
-license: cc-by-nc-sa-4.0
+license: apache-2.0
+tags:
+- automatic-speech-recognition
+- Finnish parliament data slow samples 300h
+- generated_from_trainer
+model-index:
+- name: nhan_wav2vec2-xls-r-300m-finnish-ent-10
+  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. -->
+
+# nhan_wav2vec2-xls-r-300m-finnish-ent-10
+
+This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the FINNISH PARLIAMENT DATA SLOW SAMPLES 300H - FI-FI dataset.
+It achieves the following results on the evaluation set:
+- Loss: 196.9006
+- Cer: 0.0178
+- Wer: 0.0592
+
+## 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: 5e-05
+- train_batch_size: 128
+- eval_batch_size: 128
+- seed: 1011
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 10.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Cer    | Validation Loss | Wer    |
+|:-------------:|:-----:|:-----:|:------:|:---------------:|:------:|
+| 409.2657      | 0.47  | 500   | 1.0    | 409.9399        | 1.0    |
+| 242.0796      | 0.94  | 1000  | 0.0762 | 222.4043        | 0.4204 |
+| 214.4323      | 1.4   | 1500  | 0.0342 | 205.3006        | 0.1620 |
+| 208.1767      | 1.87  | 2000  | 0.0261 | 201.7304        | 0.1095 |
+| 205.3693      | 2.34  | 2500  | 0.0248 | 200.3012        | 0.1037 |
+| 204.3477      | 2.81  | 3000  | 0.0219 | 199.3383        | 0.0830 |
+| 202.9748      | 3.28  | 3500  | 0.0207 | 199.1589        | 0.0782 |
+| 201.9818      | 3.75  | 4000  | 0.0207 | 198.5560        | 0.0769 |
+| 201.8992      | 4.21  | 4500  | 0.0201 | 198.0990        | 0.0724 |
+| 201.6079      | 4.68  | 5000  | 0.0209 | 197.8516        | 0.0712 |
+| 200.6187      | 5.15  | 5500  | 0.0191 | 197.6185        | 0.0667 |
+| 200.5608      | 5.62  | 6000  | 0.0189 | 197.5194        | 0.0658 |
+| 200.1649      | 6.09  | 6500  | 0.0191 | 197.3655        | 0.0641 |
+| 200.1713      | 6.55  | 7000  | 0.0186 | 197.2977        | 0.0629 |
+| 200.1245      | 7.02  | 7500  | 0.0193 | 197.0914        | 0.0638 |
+| 199.5289      | 7.49  | 8000  | 0.0181 | 197.0704        | 0.0608 |
+| 199.4458      | 7.96  | 8500  | 0.0183 | 196.9986        | 0.0606 |
+| 199.1502      | 8.43  | 9000  | 0.0178 | 197.0260        | 0.0590 |
+| 199.4437      | 8.9   | 9500  | 0.0180 | 196.9412        | 0.0595 |
+| 198.8669      | 9.36  | 10000 | 196.8834| 0.0180          | 0.0600 |
+| 199.1329      | 9.83  | 10500 | 196.9176| 0.0178          | 0.0591 |
+
+
+### Framework versions
+
+- Transformers 4.18.0
+- Pytorch 1.12.0.dev20220305
+- Datasets 1.18.4.dev0
+- Tokenizers 0.11.6

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 10.0,
+    "eval_cer": 0.017841032626644174,
+    "eval_loss": 196.900634765625,
+    "eval_runtime": 2576.7481,
+    "eval_samples": 34170,
+    "eval_samples_per_second": 13.261,
+    "eval_steps_per_second": 0.104,
+    "eval_wer": 0.05917507718071473,
+    "train_loss": 21.992585440074908,
+    "train_runtime": 18762.4754,
+    "train_samples": 136678,
+    "train_samples_per_second": 72.846,
+    "train_steps_per_second": 0.569
+}

config.json

@@ -0,0 +1,107 @@
+{
+  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
+  "activation_dropout": 0.055,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForECTC"
+  ],
+  "attention_dropout": 0.094,
+  "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": 0.04,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.047,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.041,
+  "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_prob": 0.082,
+  "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": 0,
+  "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": "4.18.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 33,
+  "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,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7c57bee0b987e855a5851dafa839034be0b40f9838aac082f2d1c202f308e96
+size 1262034033

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}

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": "|", "replace_word_delimiter_char": " ", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf740d4d2e16ae0e135d3e57927c6dbfdcaba5e79039717a59b7555f22c3afa5
+size 3183

vocab.json

@@ -0,0 +1 @@
+{"'": 1, "a": 2, "b": 3, "c": 4, "d": 5, "e": 6, "f": 7, "g": 8, "h": 9, "i": 10, "j": 11, "k": 12, "l": 13, "m": 14, "n": 15, "o": 16, "p": 17, "q": 18, "r": 19, "s": 20, "t": 21, "u": 22, "v": 23, "w": 24, "x": 25, "y": 26, "z": 27, "ä": 28, "å": 29, "ö": 30, "|": 32, "[UNK]": 31, "[PAD]": 0}