Upload folder using huggingface_hub

README.md

@@ -0,0 +1,97 @@
+---
+language:
+- de
+license: apache-2.0
+base_model: facebook/wav2vec2-large-xlsr-53
+tags:
+- automatic-speech-recognition
+- mozilla-foundation/common_voice_13_0
+- generated_from_trainer
+datasets:
+- common_voice_13_0
+metrics:
+- wer
+model-index:
+- name: wav2vec2-large-xlsr-53-german-cv13-restart
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: MOZILLA-FOUNDATION/COMMON_VOICE_13_0 - DE
+      type: common_voice_13_0
+      config: de
+      split: test
+      args: 'Config: de, Training split: train+validation, Eval split: test'
+    metrics:
+    - name: Wer
+      type: wer
+      value: 0.10748248671697858
+---
+
+<!-- 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-german-cv13-restart
+
+This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the MOZILLA-FOUNDATION/COMMON_VOICE_13_0 - DE dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1121
+- Wer: 0.1075
+- Cer: 0.0286
+
+## 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: 16
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.01
+- num_epochs: 15.0
+
+### Training results
+
+| Training Loss | Epoch | Step  | Cer    | Validation Loss | Wer    |
+|:-------------:|:-----:|:-----:|:------:|:---------------:|:------:|
+| 0.1679        | 1.0   | 4348  | 0.0459 | 0.1617          | 0.1707 |
+| 0.1597        | 2.0   | 8697  | 0.0479 | 0.1592          | 0.1717 |
+| 0.1364        | 3.0   | 13045 | 0.0425 | 0.1524          | 0.1563 |
+| 0.1311        | 4.0   | 17394 | 0.0406 | 0.1446          | 0.1515 |
+| 0.1152        | 5.0   | 21742 | 0.0397 | 0.1431          | 0.1470 |
+| 0.107         | 6.0   | 26091 | 0.0369 | 0.1382          | 0.1377 |
+| 0.0957        | 7.0   | 30439 | 0.0373 | 0.1343          | 0.1372 |
+| 0.0924        | 8.0   | 34788 | 0.0355 | 0.1335          | 0.1315 |
+| 0.0835        | 9.0   | 39136 | 0.0384 | 0.1328          | 0.1380 |
+| 0.0775        | 10.0  | 43485 | 0.0328 | 0.1232          | 0.1229 |
+| 0.0752        | 11.0  | 47833 | 0.0309 | 0.1220          | 0.1174 |
+| 0.0691        | 12.0  | 52182 | 0.0327 | 0.1182          | 0.1197 |
+| 0.0689        | 13.0  | 56530 | 0.0307 | 0.1163          | 0.1150 |
+| 0.0653        | 14.0  | 60879 | 0.0304 | 0.1141          | 0.1126 |
+| 0.0717        | 15.0  | 65220 | 0.1121 | 0.1075          | 0.0286 |
+
+
+### Framework versions
+
+- Transformers 4.34.0
+- Pytorch 2.1.0+cu121
+- Datasets 2.14.5
+- Tokenizers 0.14.0

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "</s>": 34,
+  "<s>": 33,
+  "[PAD]": 32,
+  "[UNK]": 31
+}

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 15.0,
+    "eval_cer": 0.028607112182745118,
+    "eval_loss": 0.11205731332302094,
+    "eval_runtime": 403.6365,
+    "eval_samples": 16143,
+    "eval_samples_per_second": 39.994,
+    "eval_steps_per_second": 2.5,
+    "eval_wer": 0.10748248671697858,
+    "train_loss": 0.0045058862668025425,
+    "train_runtime": 16814.3798,
+    "train_samples": 556578,
+    "train_samples_per_second": 496.52,
+    "train_steps_per_second": 3.879
+}

config.json

@@ -0,0 +1,116 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "activation_dropout": 0.05,
+  "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": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.05,
+  "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": 32,
+  "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": "4.34.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 35,
+  "xvector_output_dim": 512
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 15.0,
+    "eval_cer": 0.028607112182745118,
+    "eval_loss": 0.11205731332302094,
+    "eval_runtime": 403.6365,
+    "eval_samples": 16143,
+    "eval_samples_per_second": 39.994,
+    "eval_steps_per_second": 2.5,
+    "eval_wer": 0.10748248671697858
+}

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
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b534ef5793d0024013681f5531d991a998a8bbb60ce8ebf8ac7ba99cc4337f08
+size 1262045866

runs/Nov07_15-13-37_ipc13112/events.out.tfevents.1699371922.ipc13112.514063.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b678ac729d0dfedb090226de0e7794e04d8bf4e0d01412ec85616d6f3d1674e0
+size 29792

runs/Nov07_15-13-37_ipc13112/events.out.tfevents.1699389140.ipc13112.514063.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34fc3a2065e551c2cb4c528493cd90c78a11a4aedc1b7df3c178896167a1d1ed
+size 460

runs/Oct30_14-54-33_ipc13112/events.out.tfevents.1698679694.ipc13112.2331418.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:088cf721fe1421d004968f6b3b6870ec2896a1788acd23e2662bfbea400a7d35
+size 336597

special_tokens_map.json

@@ -0,0 +1,10 @@
+{
+  "additional_special_tokens": [
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,53 @@
+{
+  "added_tokens_decoder": {
+    "31": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "34": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<s>",
+    "</s>"
+  ],
+  "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",
+  "tokenizer_file": null,
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 15.0,
+    "train_loss": 0.0045058862668025425,
+    "train_runtime": 16814.3798,
+    "train_samples": 556578,
+    "train_samples_per_second": 496.52,
+    "train_steps_per_second": 3.879
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50c6500a9c13e03c9d0e120e7457927ff15567dcf31c81b4373bcc29fdd978da
+size 4600

vocab.json

@@ -0,0 +1,35 @@
+{
+  "[PAD]": 32,
+  "[UNK]": 31,
+  "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,
+  "ß": 27,
+  "ä": 28,
+  "ö": 29,
+  "ü": 30
+}