End of training

README.md

@@ -1,13 +1,13 @@
 ---
 library_name: transformers
 language:
-- hi
+- km
 license: apache-2.0
 base_model: openai/whisper-small
 tags:
 - generated_from_trainer
 datasets:
-- mozilla-foundation/common_voice_11_0
+- Khmer_speech_dataset
 metrics:
 - wer
 model-index:
@@ -17,15 +17,13 @@ model-index:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: Common Voice 11.0
-      type: mozilla-foundation/common_voice_11_0
-      config: hi
-      split: None
-      args: 'config: hi, split: test'
+      name: Khmer_voice
+      type: Khmer_speech_dataset
+      args: 'config: km, split: test'
     metrics:
     - name: Wer
       type: wer
-      value: 46.165241682891725
+      value: 79.34426229508198
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,10 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Whisper Small Hi - Sanchit Gandhi
 
-This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Khmer_voice dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4034
-- Wer: 46.1652
+- Loss: 0.6083
+- Wer: 79.3443
 
 ## Model description
 
@@ -67,15 +65,15 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Wer     |
-|:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.3874        | 0.0612 | 200  | 0.4768          | 51.3163 |
-| 0.3332        | 0.1223 | 400  | 0.4034          | 46.1652 |
+| Training Loss | Epoch  | Step | Validation Loss | Wer      |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 0.3396        | 0.2899 | 200  | 0.6831          | 119.3443 |
+| 0.1706        | 0.5797 | 400  | 0.6083          | 79.3443  |
 
 
 ### Framework versions
 
 - Transformers 4.49.0
 - Pytorch 2.6.0+cu124
-- Datasets 3.4.0
-- Tokenizers 0.21.0
+- Datasets 3.4.1
+- Tokenizers 0.21.1

generation_config.json

@@ -150,7 +150,7 @@
     "<|yo|>": 50325,
     "<|zh|>": 50260
   },
-  "language": "hindi",
+  "language": "km",
   "max_initial_timestamp_index": 50,
   "max_length": 448,
   "no_timestamps_token_id": 50363,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03c4d75082c715320e373358b35ce02cdf1a79739927d041e1d44c317a7b6f6f
+oid sha256:ff633e856deddf8c4a4608d6f1ca5909f6347bf72e6fc61b80acaa65768d32d8
 size 966995080