End of training

README.md

@@ -24,7 +24,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 16.060365369340744
+      value: 15.583796664019061
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -34,8 +34,8 @@ 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 Chinese English dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3722
-- Wer: 16.0604
+- Loss: 0.3553
+- Wer: 15.5838
 
 ## Model description
 
@@ -57,19 +57,18 @@ The following hyperparameters were used during training:
 - learning_rate: 1e-05
 - train_batch_size: 2
 - eval_batch_size: 1
-- seed: 43
+- seed: 44
 - 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: 1500
+- training_steps: 1000
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.1887        | 1.6667 | 500  | 0.3696          | 17.6172 |
-| 0.0143        | 3.3333 | 1000 | 0.3665          | 15.6632 |
-| 0.0115        | 5.0    | 1500 | 0.3722          | 16.0604 |
+| 0.2725        | 1.6667 | 500  | 0.3502          | 15.8380 |
+| 0.0209        | 3.3333 | 1000 | 0.3553          | 15.5838 |
 
 
 ### Framework versions

generation_config.json

@@ -150,7 +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