swiss german xlsr 1b

config.json

@@ -0,0 +1,108 @@
+{
+  "_name_or_path": "./stt2/checkpoint-2500/",
+  "activation_dropout": 0.0,
+  "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": 1024,
+  "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": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 7,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "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": 48,
+  "num_negatives": 100,
+  "output_hidden_size": 1280,
+  "pad_token_id": 31,
+  "proj_codevector_dim": 1024,
+  "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": "4.16.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 34,
+  "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 sha256:9d3501c55cead284c0c67a3c196bacbe69f1e04b15df325ce70bb761352438fe
+size 3850486961

trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9345063538611926,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.98,
+      "learning_rate": 9.604743083003954e-06,
+      "loss": 0.6182,
+      "step": 500
+    },
+    {
+      "epoch": 0.98,
+      "eval_loss": 0.9411023259162903,
+      "eval_runtime": 332.4611,
+      "eval_samples_per_second": 10.94,
+      "eval_steps_per_second": 1.369,
+      "eval_wer": 0.4075747711867652,
+      "step": 500
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 9.110671936758893e-06,
+      "loss": 0.5421,
+      "step": 1000
+    },
+    {
+      "epoch": 1.96,
+      "eval_loss": 0.9645132422447205,
+      "eval_runtime": 331.2591,
+      "eval_samples_per_second": 10.979,
+      "eval_steps_per_second": 1.374,
+      "eval_wer": 0.4025198177153142,
+      "step": 1000
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 8.616600790513835e-06,
+      "loss": 0.4882,
+      "step": 1500
+    },
+    {
+      "epoch": 2.93,
+      "eval_loss": 1.0171494483947754,
+      "eval_runtime": 334.3973,
+      "eval_samples_per_second": 10.876,
+      "eval_steps_per_second": 1.361,
+      "eval_wer": 0.4008922758779152,
+      "step": 1500
+    }
+  ],
+  "max_steps": 10220,
+  "num_train_epochs": 20,
+  "total_flos": 6.161659150250572e+19,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4c2914481f0517a21cdd6f997409e2ce3eb7bc757e5bc32a4a3ff5da4f0edd3
+size 2991