Simonom/uzbek-stt-v2-3k-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: 1.0283
+- Loss: 0.8509
 
 ## Model description
 
@@ -51,8 +51,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.2474        | 1.0   | 151  | 1.1499          |
-| 0.7354        | 2.0   | 302  | 1.0283          |
+| 1.1762        | 1.0   | 907  | 0.9668          |
+| 0.6511        | 2.0   | 1814 | 0.8509          |
 
 
 ### Framework versions

adapter_config.json

@@ -23,8 +23,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea3cd413d69be8523b94d5b7de35ba9795a18967b7955246e8a45c0c3e028c51
+oid sha256:bb637d2e2a0c2862dde51e1291a43ae1a1acd70806d34d47b0099670bfd8ae6b
 size 15782928

runs/May14_07-20-26_a02473d3940c/events.out.tfevents.1715671227.a02473d3940c.652.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d881a18d20712fdbd0ba3abfe90f69419faf113fac308ce9f20b42a82a3a72b
+size 22172

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b5ad3e42e46e5f7c7d76d1d8b10987d4a5e035a4cd3c54129de5529d68c30eb
+oid sha256:0abc6b7777b78383092e7db2d51176beed78b160561371bfd7425928dbdcb7a7
 size 5240