End of training

README.md

@@ -16,6 +16,15 @@ should probably proofread and complete it, then remove this comment. -->
 # whisper-tiny-polyai-enUS
 
 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:
+- eval_loss: 0.7582
+- eval_wer_ortho: 0.3510
+- eval_wer: 0.3418
+- eval_runtime: 34.041
+- eval_samples_per_second: 3.32
+- eval_steps_per_second: 0.118
+- epoch: 26.67
+- step: 400
 
 ## Model description
 
@@ -35,8 +44,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant_with_warmup

generation_config.json

@@ -35,11 +35,15 @@
   "forced_decoder_ids": [
     [
       1,
-      null
+      50259
     ],
     [
       2,
       50359
+    ],
+    [
+      3,
+      50363
     ]
   ],
   "is_multilingual": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6789410cfcf94bb4a5caf8047dfce105e1bd46f53d86a020f2c508573beb6950
+oid sha256:fe990aa13e97ce1da240b938fec3da448b20c1509b4ef3729a795906104026d3
 size 151061672