End of training

README.md

@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5638
-- Wer Ortho: 63.8900
-- Wer: 63.8689
+- Loss: 2.1113
+- Wer Ortho: 99.7982
+- Wer: 99.7579
 
 ## Model description
 
@@ -46,19 +46,19 @@ The following hyperparameters were used during training:
 - 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: constant_with_warmup
 - lr_scheduler_warmup_steps: 50
-- training_steps: 1000
+- training_steps: 500
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer Ortho | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:---------:|:-------:|
-| 0.3486        | 4.9505 | 1000 | 0.5638          | 63.8900   | 63.8689 |
+| 0.7937        | 1.9531 | 500  | 2.1113          | 99.7982   | 99.7579 |
 
 
 ### Framework versions
 
-- Transformers 4.51.3
+- Transformers 4.52.4
 - Pytorch 2.6.0+cu124
 - Datasets 3.6.0
 - Tokenizers 0.21.2

generation_config.json

@@ -1,5 +1,4 @@
 {
-  "_from_model_config": true,
   "alignment_heads": [
     [
       2,
@@ -33,6 +32,16 @@
   "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,
@@ -141,7 +150,96 @@
   "pad_token_id": 50257,
   "prev_sot_token_id": 50361,
   "return_timestamps": 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
+  ],
   "task_to_id": {
     "transcribe": 50359,
     "translate": 50358