End of training

README.md

@@ -8,19 +8,19 @@ tags:
 metrics:
 - wer
 model-index:
-- name: Whisper Small Hi - CKS 1111 gramin dataset over common voice
+- name: Whisper Small Hi - CKS 111102 gramin dataset over common voice
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# Whisper Small Hi - CKS 1111 gramin dataset over common voice
+# Whisper Small Hi - CKS 111102 gramin dataset over common voice
 
 This model is a fine-tuned version of [fine tuned openai/whisper-small](https://huggingface.co/fine tuned openai/whisper-small) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1661
-- Wer: 21.6569
+- Loss: 0.2500
+- Wer: 27.5791
 
 ## Model description
 
@@ -45,16 +45,19 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 1
-- training_steps: 2
+- lr_scheduler_warmup_steps: 100
+- training_steps: 500
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.2145        | 0.02  | 1    | 0.1826          | 24.9480 |
-| 0.2324        | 0.04  | 2    | 0.1661          | 21.6569 |
+| 0.2056        | 1.92  | 100  | 0.1679          | 27.0708 |
+| 0.065         | 3.85  | 200  | 0.2057          | 28.1062 |
+| 0.0153        | 5.77  | 300  | 0.2324          | 28.0873 |
+| 0.0031        | 7.69  | 400  | 0.2461          | 27.5979 |
+| 0.0013        | 9.62  | 500  | 0.2500          | 27.5791 |
 
 
 ### Framework versions

generation_config.json

@@ -6,6 +6,20 @@
   "bos_token_id": 50257,
   "decoder_start_token_id": 50258,
   "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      50276
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
   "max_length": 448,
   "pad_token_id": 50257,
   "return_timestamps": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7298c868c7881648ed6b50e40bc5d0485913b8c9541e3bdb591d7b13fbc076a3
+oid sha256:f8335d6b1b23e3b0a0400a1946c7ad0dba6b7dfc805de45fcd49fafdee804e69
 size 966995080

runs/Nov12_19-08-01_16a4cfcfa22f/events.out.tfevents.1699816084.16a4cfcfa22f.20565.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df5263702b32b58b753a0d3367e6b901fc340b17fa75d0bc87ee3b1df6a69760
-size 7563
+oid sha256:e0e2ddf06a373ba4902f41aab3e62d79b952421cdcfc482c4c6c660af7dd2b24
+size 7917