Training in progress, epoch 1

config.json

@@ -0,0 +1,59 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 8000,
+  "classifier_proj_size": 256,
+  "d_model": 384,
+  "decoder_attention_heads": 6,
+  "decoder_ffn_dim": 1536,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 4,
+  "decoder_start_token_id": 8001,
+  "dropout": 0.0,
+  "dtype": "float32",
+  "encoder_attention_heads": 6,
+  "encoder_ffn_dim": 1536,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 4,
+  "eos_token_id": 8000,
+  "forced_decoder_ids": [
+    [
+      1,
+      50259
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "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_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 4,
+  "num_mel_bins": 80,
+  "pad_token_id": 8000,
+  "scale_embedding": false,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 8107
+}

generation_config.json

@@ -0,0 +1,192 @@
+{
+  "alignment_heads": [
+    [
+      2,
+      2
+    ],
+    [
+      3,
+      0
+    ],
+    [
+      3,
+      2
+    ],
+    [
+      3,
+      3
+    ],
+    [
+      3,
+      4
+    ],
+    [
+      3,
+      5
+    ]
+  ],
+  "assistant_confidence_threshold": 0.4,
+  "assistant_lookbehind": 10,
+  "begin_suppress_tokens": [],
+  "bos_token_id": 8000,
+  "decoder_start_token_id": 8001,
+  "diversity_penalty": 0.0,
+  "do_sample": false,
+  "early_stopping": false,
+  "encoder_no_repeat_ngram_size": 0,
+  "encoder_repetition_penalty": 1.0,
+  "eos_token_id": [
+    8000,
+    50257
+  ],
+  "epsilon_cutoff": 0.0,
+  "eta_cutoff": 0.0,
+  "forced_decoder_ids": [
+    [
+      1,
+      8068
+    ],
+    [
+      2,
+      8102
+    ],
+    [
+      3,
+      8106
+    ]
+  ],
+  "is_multilingual": true,
+  "lang_to_id": {
+    "<|af|>": 8070,
+    "<|am|>": 8077,
+    "<|ar|>": 8015,
+    "<|as|>": 8093,
+    "<|az|>": 8047,
+    "<|ba|>": 8098,
+    "<|be|>": 8073,
+    "<|bg|>": 8035,
+    "<|bn|>": 8045,
+    "<|bo|>": 8090,
+    "<|br|>": 8052,
+    "<|bs|>": 8058,
+    "<|ca|>": 8013,
+    "<|cs|>": 8026,
+    "<|cy|>": 8040,
+    "<|da|>": 8028,
+    "<|de|>": 8004,
+    "<|el|>": 8024,
+    "<|en|>": 8002,
+    "<|es|>": 8005,
+    "<|et|>": 8050,
+    "<|eu|>": 8053,
+    "<|fa|>": 8043,
+    "<|fi|>": 8020,
+    "<|fo|>": 8081,
+    "<|fr|>": 8008,
+    "<|gl|>": 8062,
+    "<|gu|>": 8076,
+    "<|haw|>": 8095,
+    "<|ha|>": 8097,
+    "<|he|>": 8022,
+    "<|hi|>": 8019,
+    "<|hr|>": 8034,
+    "<|ht|>": 8082,
+    "<|hu|>": 8029,
+    "<|hy|>": 8055,
+    "<|id|>": 8018,
+    "<|is|>": 8054,
+    "<|it|>": 8017,
+    "<|ja|>": 8009,
+    "<|jw|>": 8099,
+    "<|ka|>": 8072,
+    "<|kk|>": 8059,
+    "<|km|>": 8066,
+    "<|kn|>": 8049,
+    "<|ko|>": 8007,
+    "<|la|>": 8037,
+    "<|lb|>": 8088,
+    "<|ln|>": 8096,
+    "<|lo|>": 8079,
+    "<|lt|>": 8036,
+    "<|lv|>": 8044,
+    "<|mg|>": 8092,
+    "<|mi|>": 8038,
+    "<|mk|>": 8051,
+    "<|ml|>": 8039,
+    "<|mn|>": 8057,
+    "<|mr|>": 8063,
+    "<|ms|>": 8025,
+    "<|mt|>": 8086,
+    "<|my|>": 8089,
+    "<|ne|>": 8056,
+    "<|nl|>": 8014,
+    "<|nn|>": 8085,
+    "<|no|>": 8031,
+    "<|oc|>": 8071,
+    "<|pa|>": 8064,
+    "<|pl|>": 8012,
+    "<|ps|>": 8083,
+    "<|pt|>": 8010,
+    "<|ro|>": 8027,
+    "<|ru|>": 8006,
+    "<|sa|>": 8087,
+    "<|sd|>": 8075,
+    "<|si|>": 8065,
+    "<|sk|>": 8041,
+    "<|sl|>": 8048,
+    "<|sn|>": 8067,
+    "<|so|>": 8069,
+    "<|sq|>": 8060,
+    "<|sr|>": 8046,
+    "<|su|>": 8100,
+    "<|sv|>": 8016,
+    "<|sw|>": 8061,
+    "<|ta|>": 8030,
+    "<|te|>": 8042,
+    "<|tg|>": 8074,
+    "<|th|>": 8032,
+    "<|tk|>": 8084,
+    "<|tl|>": 8091,
+    "<|tr|>": 8011,
+    "<|tt|>": 8094,
+    "<|uk|>": 8023,
+    "<|ur|>": 8033,
+    "<|uz|>": 8080,
+    "<|vi|>": 8021,
+    "<|yi|>": 8078,
+    "<|yo|>": 8068,
+    "<|zh|>": 8003
+  },
+  "language": "yoruba",
+  "length_penalty": 1.0,
+  "max_initial_timestamp_index": 50,
+  "max_length": 448,
+  "min_length": 0,
+  "no_repeat_ngram_size": 0,
+  "no_timestamps_token_id": 8106,
+  "num_assistant_tokens": 20,
+  "num_assistant_tokens_schedule": "constant",
+  "num_beam_groups": 1,
+  "num_beams": 1,
+  "num_return_sequences": 1,
+  "output_scores": false,
+  "pad_token_id": 8000,
+  "prev_sot_token_id": 50361,
+  "remove_invalid_values": false,
+  "repetition_penalty": 1.0,
+  "return_dict_in_generate": false,
+  "return_timestamps": false,
+  "suppress_tokens": [],
+  "target_lookbehind": 10,
+  "task": "transcribe",
+  "task_to_id": {
+    "transcribe": 8000,
+    "translate": 8000
+  },
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "transformers_version": "5.0.0",
+  "typical_p": 1.0,
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7069a0892172186b327acecb4a704bc2957cfe8145b673b05555a307eade22c
+size 83849160

processor_config.json

@@ -0,0 +1,17 @@
+{
+  "feature_extractor": {
+    "chunk_length": 30,
+    "dither": 0.0,
+    "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,
+    "return_attention_mask": false,
+    "sampling_rate": 16000
+  },
+  "processor_class": "WhisperProcessor"
+}

tokenizer_config.json

@@ -0,0 +1,122 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": [
+    "<|startoftranscript|>",
+    "<|en|>",
+    "<|zh|>",
+    "<|de|>",
+    "<|es|>",
+    "<|ru|>",
+    "<|ko|>",
+    "<|fr|>",
+    "<|ja|>",
+    "<|pt|>",
+    "<|tr|>",
+    "<|pl|>",
+    "<|ca|>",
+    "<|nl|>",
+    "<|ar|>",
+    "<|sv|>",
+    "<|it|>",
+    "<|id|>",
+    "<|hi|>",
+    "<|fi|>",
+    "<|vi|>",
+    "<|he|>",
+    "<|uk|>",
+    "<|el|>",
+    "<|ms|>",
+    "<|cs|>",
+    "<|ro|>",
+    "<|da|>",
+    "<|hu|>",
+    "<|ta|>",
+    "<|no|>",
+    "<|th|>",
+    "<|ur|>",
+    "<|hr|>",
+    "<|bg|>",
+    "<|lt|>",
+    "<|la|>",
+    "<|mi|>",
+    "<|ml|>",
+    "<|cy|>",
+    "<|sk|>",
+    "<|te|>",
+    "<|fa|>",
+    "<|lv|>",
+    "<|bn|>",
+    "<|sr|>",
+    "<|az|>",
+    "<|sl|>",
+    "<|kn|>",
+    "<|et|>",
+    "<|mk|>",
+    "<|br|>",
+    "<|eu|>",
+    "<|is|>",
+    "<|hy|>",
+    "<|ne|>",
+    "<|mn|>",
+    "<|bs|>",
+    "<|kk|>",
+    "<|sq|>",
+    "<|sw|>",
+    "<|gl|>",
+    "<|mr|>",
+    "<|pa|>",
+    "<|si|>",
+    "<|km|>",
+    "<|sn|>",
+    "<|yo|>",
+    "<|so|>",
+    "<|af|>",
+    "<|oc|>",
+    "<|ka|>",
+    "<|be|>",
+    "<|tg|>",
+    "<|sd|>",
+    "<|gu|>",
+    "<|am|>",
+    "<|yi|>",
+    "<|lo|>",
+    "<|uz|>",
+    "<|fo|>",
+    "<|ht|>",
+    "<|ps|>",
+    "<|tk|>",
+    "<|nn|>",
+    "<|mt|>",
+    "<|sa|>",
+    "<|lb|>",
+    "<|my|>",
+    "<|bo|>",
+    "<|tl|>",
+    "<|mg|>",
+    "<|as|>",
+    "<|tt|>",
+    "<|haw|>",
+    "<|ln|>",
+    "<|ha|>",
+    "<|ba|>",
+    "<|jw|>",
+    "<|su|>",
+    "<|translate|>",
+    "<|transcribe|>",
+    "<|startoflm|>",
+    "<|startofprev|>",
+    "<|nocaptions|>",
+    "<|notimestamps|>"
+  ],
+  "language": "yoruba",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "predict_timestamps": false,
+  "processor_class": "WhisperProcessor",
+  "task": "transcribe",
+  "tokenizer_class": "WhisperTokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:689aecae5d6e68c6ddd7f0354ea17c2dcc9e19b7c2c769aadf2000330b2dd8c2
+size 5393