End of training

README.md

@@ -5,9 +5,24 @@ tags:
 - generated_from_trainer
 datasets:
 - PolyAI/minds14
+metrics:
+- wer
 model-index:
 - name: whisper-tiny-minds14-audio-course-v2
-  results: []
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: PolyAI/minds14
+      type: PolyAI/minds14
+      config: en-US
+      split: train[450:]
+      args: en-US
+    metrics:
+    - name: Wer
+      type: wer
+      value: 0.345926800472255
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,6 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
 # whisper-tiny-minds14-audio-course-v2
 
 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6485
+- Wer Ortho: 0.3492
+- Wer: 0.3459
 
 ## Model description
 
@@ -43,6 +62,14 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_steps: 50
 - training_steps: 500
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
+| 0.0089        | 8.93  | 250  | 0.5684          | 0.3677    | 0.3548 |
+| 0.0007        | 17.86 | 500  | 0.6485          | 0.3492    | 0.3459 |
+
+
 ### Framework versions
 
 - Transformers 4.32.1

generation_config.json

@@ -35,11 +35,15 @@
   "forced_decoder_ids": [
     [
       1,
-      null
+      50259
     ],
     [
       2,
       50359
+    ],
+    [
+      3,
+      50363
     ]
   ],
   "is_multilingual": true,
@@ -144,6 +148,7 @@
     "<|yo|>": 50325,
     "<|zh|>": 50260
   },
+  "language": "en",
   "max_initial_timestamp_index": 1,
   "max_length": 448,
   "no_timestamps_token_id": 50363,
@@ -239,6 +244,7 @@
     50361,
     50362
   ],
+  "task": "transcribe",
   "task_to_id": {
     "transcribe": 50359,
     "translate": 50358