update model card README.md

README.md

@@ -1,41 +1,38 @@
 ---
-language:
-- eu
 license: apache-2.0
 tags:
-- whisper-event
 - generated_from_trainer
 datasets:
-- mozilla-foundation/common_voice_13_0
+- common_voice_16_0
 metrics:
 - wer
 model-index:
-- name: Whisper Small Basque
+- name: openai/whisper-small
   results:
   - task:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: mozilla-foundation/common_voice_13_0 eu
-      type: mozilla-foundation/common_voice_13_0
+      name: common_voice_16_0
+      type: common_voice_16_0
       config: eu
       split: test
       args: eu
     metrics:
     - name: Wer
       type: wer
-      value: 18.775568066750374
+      value: 12.012786552211754
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# Whisper Small Basque
+# openai/whisper-small
 
-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 eu dataset.
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the common_voice_16_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3812
-- Wer: 18.7756
+- Loss: 0.1996
+- Wer: 12.0128
 
 ## Model description
 
@@ -43,7 +40,7 @@ More information needed
 
 ## Intended uses & limitations
 
-If you need to use this model with [whisper.cpp](https://github.com/ggerganov/whisper.cpp), you can download the ggml file: [ggml-small-eu.bin](https://huggingface.co/xezpeleta/whisper-small-eu/blob/main/ggml-small.eu.bin)
+More information needed
 
 ## Training and evaluation data
 
@@ -68,11 +65,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.1413        | 2.04  | 1000 | 0.3178          | 22.0139 |
-| 0.0181        | 4.07  | 2000 | 0.3376          | 20.2864 |
-| 0.0044        | 7.02  | 3000 | 0.3603          | 18.8768 |
-| 0.0016        | 9.06  | 4000 | 0.3812          | 18.7756 |
-| 0.0012        | 12.01 | 5000 | 0.3914          | 18.8302 |
+| 0.2009        | 1.04  | 1000 | 0.2446          | 17.6881 |
+| 0.0759        | 2.09  | 2000 | 0.2102          | 14.2584 |
+| 0.0264        | 3.13  | 3000 | 0.2200          | 13.6898 |
+| 0.0633        | 5.02  | 4000 | 0.1955          | 12.5535 |
+| 0.0199        | 6.06  | 5000 | 0.1996          | 12.0128 |
 
 
 ### Framework versions

nohup.out

@@ -70580,3 +70580,21 @@ Training completed. Do not forget to share your model on huggingface.co/models =
 [INFO|configuration_utils.py:447] 2023-12-29 22:52:36,152 >> Configuration saved in ./config.json
 [INFO|modeling_utils.py:1693] 2023-12-29 22:52:38,093 >> Model weights saved in ./pytorch_model.bin
 [INFO|feature_extraction_utils.py:368] 2023-12-29 22:52:38,106 >> Feature extractor saved in ./preprocessor_config.json
+Several commits (2) will be pushed upstream.
+{'eval_loss': 0.19964517652988434, 'eval_wer': 12.012786552211754, 'eval_runtime': 1705.0556, 'eval_samples_per_second': 7.34, 'eval_steps_per_second': 0.459, 'epoch': 6.06}
+{'train_runtime': 29005.3522, 'train_samples_per_second': 5.516, 'train_steps_per_second': 0.172, 'train_loss': 0.15837200704216958, 'epoch': 6.06}
+12/29/2023 22:52:44 - WARNING - huggingface_hub.repository - Several commits (2) will be pushed upstream.
+The progress bars may be unreliable.
+12/29/2023 22:52:44 - WARNING - huggingface_hub.repository - The progress bars may be unreliable.
+
+
+
+
+   202b623..df538ec  main -> main
+
+12/29/2023 22:56:25 - WARNING - huggingface_hub.repository - To https://huggingface.co/xezpeleta/whisper-small-eu
+   202b623..df538ec  main -> main
+
+
+
+