Model save

README.md

@@ -1,4 +1,6 @@
 ---
+license: apache-2.0
+base_model: openai/whisper-tiny
 tags:
 - generated_from_trainer
 metrics:
@@ -13,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # whisper-tiny-hi2_test
 
-This model was trained from scratch on the None dataset.
+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: 0.6505
-- Wer: 69.9890
+- Loss: 0.5504
+- Wer: 63.9035
 
 ## Model description
 
@@ -35,12 +37,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 3.75e-05
 - train_batch_size: 32
 - eval_batch_size: 1
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_steps: 50
 - training_steps: 200
 - mixed_precision_training: Native AMP
 
@@ -48,11 +51,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 1.2169        | 1.25  | 40   | 1.0360          | 91.6081 |
-| 0.7302        | 2.5   | 80   | 0.7369          | 79.8035 |
-| 0.5917        | 3.75  | 120  | 0.6505          | 69.9890 |
-| 0.5156        | 5.0   | 160  | 0.6157          | 70.4293 |
-| 0.481         | 6.25  | 200  | 0.6051          | 70.0398 |
+| 0.6803        | 1.25  | 40   | 0.6102          | 65.9441 |
+| 0.3649        | 2.5   | 80   | 0.5037          | 58.3150 |
+| 0.2296        | 3.75  | 120  | 0.4897          | 66.7146 |
+| 0.1564        | 5.0   | 160  | 0.5131          | 65.3429 |
+| 0.0905        | 6.25  | 200  | 0.5504          | 63.9035 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2644a276d865ced1c092576cf9345e8376a5cbf8ccb536ac738a6ed3e094caeb
+oid sha256:daeea7778cdeda935a2e90f442518eb60512721cd10bce0921a80c47aa8f2543
 size 151061672

whisper-tiny-hi-checkpoint-1/config.json

@@ -19,7 +19,7 @@
   "decoder_layerdrop": 0.0,
   "decoder_layers": 4,
   "decoder_start_token_id": 50258,
-  "dropout": 0.0,
+  "dropout": 0.1,
   "encoder_attention_heads": 6,
   "encoder_ffn_dim": 1536,
   "encoder_layerdrop": 0.0,

whisper-tiny-hi-checkpoint-1/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a59c8982089b3ffb0f35b2a8b93a329827d3603f741f4d47ddb7a17dc5a7e5e2
+oid sha256:daeea7778cdeda935a2e90f442518eb60512721cd10bce0921a80c47aa8f2543
 size 151061672

whisper-tiny-hi-checkpoint-1/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c982fa9327e2e49f4765e9f4a5be54ca2c672121610ce55b8168505a2beb3b7
+oid sha256:37c1d71d4573028fde34dd156869c75306de202ae193d1b60195dcab72289f8d
 size 5240