Simonom/uzbek-stt-v2-2.5k-data

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the common_voice_14_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8509
+- Loss: 0.7569
 
 ## Model description
 
@@ -51,14 +51,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.1762        | 1.0   | 907  | 0.9668          |
-| 0.6511        | 2.0   | 1814 | 0.8509          |
+| 0.9643        | 1.0   | 1209 | 0.8721          |
+| 0.5618        | 2.0   | 2418 | 0.7569          |
 
 
 ### Framework versions
 
-- PEFT 0.10.1.dev0
-- Transformers 4.41.0.dev0
+- PEFT 0.11.2.dev0
+- Transformers 4.42.0.dev0
 - Pytorch 2.2.1+cu121
 - Datasets 2.19.1
 - Tokenizers 0.19.1

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb637d2e2a0c2862dde51e1291a43ae1a1acd70806d34d47b0099670bfd8ae6b
+oid sha256:e1e1467526d306e2b68c4234a07301dfafd11e24c6df0f420149274ef431d28c
 size 15782928

runs/May21_08-12-09_5c7a02fa1a89/events.out.tfevents.1716279130.5c7a02fa1a89.938.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c678b266887327f2a91516987d7ace9029e08453545a83037cdb18dd1f023314
+size 7139

runs/May21_08-23-31_5c7a02fa1a89/events.out.tfevents.1716279812.5c7a02fa1a89.7458.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5eef4216214f72b918900c510af24949971fa1e667aba4231a42f928e2bf2a8
+size 27236

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0abc6b7777b78383092e7db2d51176beed78b160561371bfd7425928dbdcb7a7
+oid sha256:6ef957a6ecf94163d88a231546fede3ea59eb17da7a023438b7bb8a9908bae2f
 size 5240