Training in progress, epoch 1

config.json

@@ -0,0 +1,95 @@
+{
+  "_name_or_path": "hf-internal-testing/tiny-random-UniSpeechSatModel",
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "UniSpeechSatForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "conv_dim": [
+    32,
+    32,
+    32
+  ],
+  "conv_kernel": [
+    8,
+    8,
+    8
+  ],
+  "conv_stride": [
+    4,
+    4,
+    4
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 16,
+  "id2label": {
+    "0": "nor",
+    "1": "mild",
+    "2": "mod",
+    "3": "sev"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 20,
+  "label2id": {
+    "mild": 1,
+    "mod": 2,
+    "nor": 0,
+    "sev": 3
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 2,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.5,
+  "model_type": "unispeech-sat",
+  "num_attention_heads": 2,
+  "num_clusters": 504,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 2,
+  "num_conv_pos_embeddings": 16,
+  "num_feat_extract_layers": 3,
+  "num_hidden_layers": 4,
+  "num_negatives": 100,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 256,
+  "tdnn_dilation": [
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    32,
+    32
+  ],
+  "tdnn_kernel": [
+    3,
+    3
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 32
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44a37bfaf9e1c63a4da40e8334acaeb6c044a85a4203ad3b18d254c2ab74a8c1
+size 138080

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
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:219b4b12d798dd7ee02424062e51bf70e13d563f47b8dd8d564f0138d72c54a9
+size 5368