Training in progress, step 28

config.json

@@ -0,0 +1,74 @@
+{
+  "_name_or_path": "openai/whisper-large-v3",
+  "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": 1280,
+  "decoder_attention_heads": 20,
+  "decoder_ffn_dim": 5120,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 32,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 20,
+  "encoder_ffn_dim": 5120,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 32,
+  "eos_token_id": 50257,
+  "id2label": {
+    "0": "blues",
+    "1": "classical",
+    "2": "country",
+    "3": "disco",
+    "4": "hiphop",
+    "5": "jazz",
+    "6": "metal",
+    "7": "pop",
+    "8": "reggae",
+    "9": "rock"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "blues": "0",
+    "classical": "1",
+    "country": "2",
+    "disco": "3",
+    "hiphop": "4",
+    "jazz": "5",
+    "metal": "6",
+    "pop": "7",
+    "reggae": "8",
+    "rock": "9"
+  },
+  "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": 32,
+  "num_mel_bins": 128,
+  "pad_token_id": 50256,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51866
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b50cb5355f983f4c2ddb0980cb1268151a72a7d81692de3aeea941f64e8eff60
+size 2549252296

preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "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/Feb13_21-28-11_rocket/events.out.tfevents.1707827297.rocket.2069110.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77c92f9b3f336c1c65c2064bb6c54c760e910b4d8ec9ba95c51e2387fc085297
+size 5428

runs/Feb13_21-35-35_rocket/events.out.tfevents.1707827742.rocket.2076745.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0108540669a7f075595963b72c9a16d3e6cf79dbcfab81c773ff64a01d8ced33
+size 6669

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81197e5025744964bd157b9fa863747f72a507d865bdade678b7ed7f1af6ea3a
+size 4728