Training in progress, epoch 1

config.json

@@ -0,0 +1,71 @@
+{
+  "_name_or_path": "vinai/PhoWhisper-small",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForAudioClassification"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": null,
+  "id2label": {
+    "0": "male, northern dialect",
+    "1": "male, central dialect",
+    "2": "male, highland central dialect",
+    "3": "male, southern dialect",
+    "4": "female, northern dialect",
+    "5": "female, central dialect",
+    "6": "female, highland central dialect",
+    "7": "female, southern dialect"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "female, central dialect": "5",
+    "female, highland central dialect": "6",
+    "female, northern dialect": "4",
+    "female, southern dialect": "7",
+    "male, central dialect": "1",
+    "male, highland central dialect": "2",
+    "male, northern dialect": "0",
+    "male, southern dialect": "3"
+  },
+  "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": 0.05,
+  "max_length": 448,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 12,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e408d922135ed421250a1c00f76500dcb8e31b42d5559099405f7074ce6952bc
+size 353432528

preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 80,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

runs/Jul07_12-35-10_f2f65e57c46c/events.out.tfevents.1720355711.f2f65e57c46c.3178.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6260be2e6c184b919f9bba0cc9df3c293a3243a578f6ec25473b0543c354b35a
+size 9892

runs/Jul07_12-54-15_f2f65e57c46c/events.out.tfevents.1720356856.f2f65e57c46c.4167.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe0267ae9b8186cd76865f032b5666bff78a7fee008eb767ee6023c0a779b105
+size 50488

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be9e0a1d4c83e80cfdcb25156e372c9f10b816122e0940a011d97db6b2f9cc3d
+size 5176