end of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 12.22,
+    "eval_loss": 0.45190635323524475,
+    "eval_runtime": 704.8504,
+    "eval_samples": 2894,
+    "eval_samples_per_second": 4.106,
+    "eval_steps_per_second": 0.257,
+    "eval_wer": 32.011343435198505,
+    "train_loss": 0.06323314253110439,
+    "train_runtime": 16800.4503,
+    "train_samples": 6540,
+    "train_samples_per_second": 4.762,
+    "train_steps_per_second": 0.298
+}

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "openai/whisper-small",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "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,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_length": 448,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "model_type": "whisper",
+  "num_hidden_layers": 12,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "suppress_tokens": [],
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.0.dev0",
+  "use_cache": true,
+  "vocab_size": 51865
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 12.22,
+    "eval_loss": 0.45190635323524475,
+    "eval_runtime": 704.8504,
+    "eval_samples": 2894,
+    "eval_samples_per_second": 4.106,
+    "eval_steps_per_second": 0.257,
+    "eval_wer": 32.011343435198505
+}