trained on CommonVoice13 50%-100%

README.md

@@ -5,14 +5,12 @@ license: apache-2.0
 base_model: openai/whisper-small
 tags:
 - automatic-speech-recognition
+- generated_from_trainer
 metrics:
 - wer
 model-index:
 - name: Whisper Small Uzbek
   results: []
-datasets:
-- mozilla-foundation/common_voice_13_0
-pipeline_tag: automatic-speech-recognition
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -22,9 +20,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the mozilla-foundation/common_voice_13_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6155
-- Wer Ortho: 54.5846
-- Wer: 42.7596
+- Loss: 0.5058
+- Wer Ortho: 45.0514
+- Wer: 34.8505
 
 ## Model description
 
@@ -57,7 +55,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
-| 0.7298        | 0.27  | 500  | 0.6155          | 54.5846   | 42.7596 |
+| 0.4898        | 0.27  | 500  | 0.5058          | 45.0514   | 34.8505 |
 
 
 ### Framework versions
@@ -65,4 +63,4 @@ The following hyperparameters were used during training:
 - Transformers 4.35.2
 - Pytorch 2.1.0+cu118
 - Datasets 2.15.0
-- Tokenizers 0.15.0
+- Tokenizers 0.15.0

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/whisper-small",
+  "_name_or_path": "mirodil/whisper-small-uzbek",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c92f58898b9736b86e5453cb5779383ef5d402929e89d9ac79ce829761c83abf
+oid sha256:7ddcff05ba8d5cf40cd7b283bf5d59a6d900165dab3481f175d32608dbb44e42
 size 966995080

runs/Nov23_00-51-14_bed9719106f8/events.out.tfevents.1700700681.bed9719106f8.2896.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f6de802c259bbcdb999b149b03fbb8f3fbf1e12b32b49ee8b4ee86e7279ce66
+size 9863

special_tokens_map.json

@@ -125,7 +125,7 @@
   "pad_token": {
     "content": "<|endoftext|>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb40810a6d02a0d3d1e2c4743e81d12f35e60d0d9b0e03d6cefd192a0830aead
+oid sha256:21931c2347a20151223a5c629b91b30885b4e3e3d3cb7c7dc6f83ed4e919e81b
 size 4728