End of training

README.md

@@ -0,0 +1,88 @@
+---
+library_name: transformers
+language:
+- jv
+license: apache-2.0
+base_model: openai/whisper-tiny
+tags:
+- whisper
+- javanese
+- asr
+- generated_from_trainer
+datasets:
+- jv_id_asr_split
+metrics:
+- wer
+model-index:
+- name: bagasshw/whisper-tiny-jv-full
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: jv_id_asr_split
+      type: jv_id_asr_split
+      config: jv_id_asr_source
+      split: None
+      args: jv_id_asr_source
+    metrics:
+    - name: Wer
+      type: wer
+      value: 16.665494031285913
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# bagasshw/whisper-tiny-jv-full
+
+This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the jv_id_asr_split dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2094
+- Wer: 16.6655
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3.75e-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- training_steps: 15000
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss | Wer     |
+|:-------------:|:------:|:-----:|:---------------:|:-------:|
+| 0.3746        | 0.3242 | 3000  | 0.3745          | 27.3677 |
+| 0.2935        | 0.6484 | 6000  | 0.2938          | 22.0987 |
+| 0.2443        | 0.9726 | 9000  | 0.2478          | 19.4102 |
+| 0.1576        | 1.2967 | 12000 | 0.2228          | 18.2353 |
+| 0.1376        | 1.6209 | 15000 | 0.2094          | 16.6655 |
+
+
+### Framework versions
+
+- Transformers 4.50.0.dev0
+- Pytorch 2.7.0+cu128
+- Datasets 2.18.0
+- Tokenizers 0.21.1

config.json

@@ -21,20 +21,7 @@
   "encoder_layerdrop": 0.0,
   "encoder_layers": 4,
   "eos_token_id": 50257,
-  "forced_decoder_ids": [
-    [
-      1,
-      50259
-    ],
-    [
-      2,
-      50359
-    ],
-    [
-      3,
-      50363
-    ]
-  ],
+  "forced_decoder_ids": null,
   "init_std": 0.02,
   "is_encoder_decoder": true,
   "mask_feature_length": 10,
@@ -53,8 +40,8 @@
   "pad_token_id": 50257,
   "scale_embedding": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.51.3",
-  "use_cache": true,
+  "transformers_version": "4.50.0.dev0",
+  "use_cache": false,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865
 }

generation_config.json

@@ -0,0 +1,159 @@
+{
+  "alignment_heads": [
+    [
+      2,
+      2
+    ],
+    [
+      3,
+      0
+    ],
+    [
+      3,
+      2
+    ],
+    [
+      3,
+      3
+    ],
+    [
+      3,
+      4
+    ],
+    [
+      3,
+      5
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      null
+    ],
+    [
+      2,
+      50359
+    ]
+  ],
+  "is_multilingual": true,
+  "lang_to_id": {
+    "<|af|>": 50327,
+    "<|am|>": 50334,
+    "<|ar|>": 50272,
+    "<|as|>": 50350,
+    "<|az|>": 50304,
+    "<|ba|>": 50355,
+    "<|be|>": 50330,
+    "<|bg|>": 50292,
+    "<|bn|>": 50302,
+    "<|bo|>": 50347,
+    "<|br|>": 50309,
+    "<|bs|>": 50315,
+    "<|ca|>": 50270,
+    "<|cs|>": 50283,
+    "<|cy|>": 50297,
+    "<|da|>": 50285,
+    "<|de|>": 50261,
+    "<|el|>": 50281,
+    "<|en|>": 50259,
+    "<|es|>": 50262,
+    "<|et|>": 50307,
+    "<|eu|>": 50310,
+    "<|fa|>": 50300,
+    "<|fi|>": 50277,
+    "<|fo|>": 50338,
+    "<|fr|>": 50265,
+    "<|gl|>": 50319,
+    "<|gu|>": 50333,
+    "<|haw|>": 50352,
+    "<|ha|>": 50354,
+    "<|he|>": 50279,
+    "<|hi|>": 50276,
+    "<|hr|>": 50291,
+    "<|ht|>": 50339,
+    "<|hu|>": 50286,
+    "<|hy|>": 50312,
+    "<|id|>": 50275,
+    "<|is|>": 50311,
+    "<|it|>": 50274,
+    "<|ja|>": 50266,
+    "<|jw|>": 50356,
+    "<|ka|>": 50329,
+    "<|kk|>": 50316,
+    "<|km|>": 50323,
+    "<|kn|>": 50306,
+    "<|ko|>": 50264,
+    "<|la|>": 50294,
+    "<|lb|>": 50345,
+    "<|ln|>": 50353,
+    "<|lo|>": 50336,
+    "<|lt|>": 50293,
+    "<|lv|>": 50301,
+    "<|mg|>": 50349,
+    "<|mi|>": 50295,
+    "<|mk|>": 50308,
+    "<|ml|>": 50296,
+    "<|mn|>": 50314,
+    "<|mr|>": 50320,
+    "<|ms|>": 50282,
+    "<|mt|>": 50343,
+    "<|my|>": 50346,
+    "<|ne|>": 50313,
+    "<|nl|>": 50271,
+    "<|nn|>": 50342,
+    "<|no|>": 50288,
+    "<|oc|>": 50328,
+    "<|pa|>": 50321,
+    "<|pl|>": 50269,
+    "<|ps|>": 50340,
+    "<|pt|>": 50267,
+    "<|ro|>": 50284,
+    "<|ru|>": 50263,
+    "<|sa|>": 50344,
+    "<|sd|>": 50332,
+    "<|si|>": 50322,
+    "<|sk|>": 50298,
+    "<|sl|>": 50305,
+    "<|sn|>": 50324,
+    "<|so|>": 50326,
+    "<|sq|>": 50317,
+    "<|sr|>": 50303,
+    "<|su|>": 50357,
+    "<|sv|>": 50273,
+    "<|sw|>": 50318,
+    "<|ta|>": 50287,
+    "<|te|>": 50299,
+    "<|tg|>": 50331,
+    "<|th|>": 50289,
+    "<|tk|>": 50341,
+    "<|tl|>": 50348,
+    "<|tr|>": 50268,
+    "<|tt|>": 50351,
+    "<|uk|>": 50280,
+    "<|ur|>": 50290,
+    "<|uz|>": 50337,
+    "<|vi|>": 50278,
+    "<|yi|>": 50335,
+    "<|yo|>": 50325,
+    "<|zh|>": 50260
+  },
+  "max_initial_timestamp_index": 50,
+  "max_length": 448,
+  "no_timestamps_token_id": 50363,
+  "pad_token_id": 50257,
+  "prev_sot_token_id": 50361,
+  "return_timestamps": false,
+  "suppress_tokens": [],
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.50.0.dev0"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf2b090d4d6832c3a41553594d3bdd0b344af851ce6e88f34227ab0754e3e655
+oid sha256:638101526fe609953d3cbd458cca71c5582c429ff8750aac57b304a0d0a4d642
 size 151061672

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e641340185408303766da6cd6172e7a8c0cac1d845f4e7ad5ee8bf5e5f2ea762
-size 5905
+oid sha256:0a510acba1c26a08f651cf1988c427f76458243f294115ccd5b6371ad599c053
+size 6033