Samandards/uzbek-5k-data

README.md

@@ -16,7 +16,7 @@ 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 None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7645
+- Loss: 0.7821
 
 ## Model description
 
@@ -49,8 +49,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.054         | 1.0   | 86   | 0.8908          |
-| 0.6785        | 2.0   | 172  | 0.7645          |
+| 1.0652        | 1.0   | 86   | 0.9028          |
+| 0.6926        | 2.0   | 172  | 0.7821          |
 
 
 ### Framework versions

adapter_config.json

@@ -1,10 +1,10 @@
 {
   "alpha_pattern": {},
   "auto_mapping": {
-    "base_model_class": "PeftModel",
-    "parent_library": "peft.peft_model"
+    "base_model_class": "WhisperForConditionalGeneration",
+    "parent_library": "transformers.models.whisper.modeling_whisper"
   },
-  "base_model_name_or_path": null,
+  "base_model_name_or_path": "openai/whisper-large-v2",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc503d8f32177c5fd85ebef3e2fd033f1843316db0bcadf94b21f0a16894dcbb
-size 7924808
+oid sha256:4798de16772b7209d4015a76168294196717d7cf53efa50c1c01278a73fca20b
+size 7918280

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d9b2f2850856b320102670f687f3b2fe0d3fc81a31e68eea2b73d9d368ba00f
+oid sha256:848d29ca659656cfadb73a102759a84e4bd0a59d31c48a96b2fa1b935abda895
 size 5304