End of training

README.md

@@ -2,22 +2,22 @@
 language:
 - mn
 license: apache-2.0
-base_model: openai/whisper-tiny
+base_model: openai/whisper-small
 tags:
 - generated_from_trainer
 datasets:
 - mozilla-foundation/common_voice_13_0
 model-index:
-- name: Whisper Tiny MN - Ochirsukh Batbold
+- name: Whisper Tiny Mn - Ochirsukh Batbold
   results: []
 ---
 
 <!-- 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. -->
 
-# Whisper Tiny MN - Ochirsukh Batbold
+# Whisper Tiny Mn - Ochirsukh Batbold
 
-This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Common Voice 13 mn dataset.
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 13 dataset.
 
 ## Model description
 
@@ -38,12 +38,12 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
 - train_batch_size: 32
-- eval_batch_size: 16
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
-- training_steps: 3
+- lr_scheduler_type: constant_with_warmup
+- lr_scheduler_warmup_steps: 50
+- training_steps: 5
 - mixed_precision_training: Native AMP
 
 ### Training results

config.json

@@ -25,7 +25,20 @@
   "encoder_layerdrop": 0.0,
   "encoder_layers": 4,
   "eos_token_id": 50257,
-  "forced_decoder_ids": null,
+  "forced_decoder_ids": [
+    [
+      1,
+      50259
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
   "init_std": 0.02,
   "is_encoder_decoder": true,
   "mask_feature_length": 10,
@@ -43,10 +56,99 @@
   "num_mel_bins": 80,
   "pad_token_id": 50257,
   "scale_embedding": false,
-  "suppress_tokens": [],
+  "suppress_tokens": [
+    1,
+    2,
+    7,
+    8,
+    9,
+    10,
+    14,
+    25,
+    26,
+    27,
+    28,
+    29,
+    31,
+    58,
+    59,
+    60,
+    61,
+    62,
+    63,
+    90,
+    91,
+    92,
+    93,
+    359,
+    503,
+    522,
+    542,
+    873,
+    893,
+    902,
+    918,
+    922,
+    931,
+    1350,
+    1853,
+    1982,
+    2460,
+    2627,
+    3246,
+    3253,
+    3268,
+    3536,
+    3846,
+    3961,
+    4183,
+    4667,
+    6585,
+    6647,
+    7273,
+    9061,
+    9383,
+    10428,
+    10929,
+    11938,
+    12033,
+    12331,
+    12562,
+    13793,
+    14157,
+    14635,
+    15265,
+    15618,
+    16553,
+    16604,
+    18362,
+    18956,
+    20075,
+    21675,
+    22520,
+    26130,
+    26161,
+    26435,
+    28279,
+    29464,
+    31650,
+    32302,
+    32470,
+    36865,
+    42863,
+    47425,
+    49870,
+    50254,
+    50258,
+    50358,
+    50359,
+    50360,
+    50361,
+    50362
+  ],
   "torch_dtype": "float32",
   "transformers_version": "4.35.2",
-  "use_cache": true,
+  "use_cache": false,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f18415ab339cdd4698ee0b660d97a4bbb6f4cca8b341772fd7381753100d9a8
+oid sha256:54949258c437ee373da926ac04154414455d0d4c8161f0d20c82828c20a423b5
 size 151061672

runs/Nov28_09-23-37_icdcub-03/events.out.tfevents.1701163436.icdcub-03

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:934c9fcd9cf58a86b3a89a06c7165c5306c93c910a870f5a31ca08bde8e538d2
+size 5956

runs/Nov28_10-19-33_icdcub-03/events.out.tfevents.1701166775.icdcub-03

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6bd47b8d20a784d2b149c8d819f95647374ed068c75ffbadf5b64351ac63d96
+size 5956

runs/Nov28_10-23-32_icdcub-03/events.out.tfevents.1701167013.icdcub-03

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4247a34d12da42733abdadc57ca7ba0886d95a2618979a80e01f41a9cbf3641
+size 5956

runs/Nov28_10-27-02_icdcub-03/events.out.tfevents.1701167224.icdcub-03

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:716bc42615079d14bb66e02ed7746278f0bbb571ed5eb5fbd88ec0c73438e893
+size 6304

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea6c6158294e02ed53b0bd13afadcb1ae65fa6bb7321698a2c59266435b85e64
+oid sha256:c40a0d185694cc56c2fc9fdd331de68ac9ab8b26f410400080e9347dee3b02fa
 size 4283