End of training

README.md

@@ -6,33 +6,34 @@ base_model: openai/whisper-tiny
 tags:
 - hf-asr-leaderboard
 - generated_from_trainer
-datasets:
-- jpdiazpardo/guturalScream_metalVocals
+metrics:
+- wer
 model-index:
-- name: "Whisper Tiny Metal - Juan Pablo D\xEDaz"
+- name: Whisper Tiny Metal - Juan Pablo Diaz
   results: []
 ---
 
-# Whisper Tiny Metal - Juan Pablo Díaz
+<!-- 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. -->
 
-This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Gutural Scream & Metal Vocals dataset.
+# Whisper Tiny Metal - Juan Pablo Diaz
+
+This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Gutural Scream and Metal Vocals dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6780
+- Wer: 79.9061
 
 ## Model description
-The model is inteded for automatic speech recognition in gutural and scream voice. The model was trained on vocals preprocessed using Spleeter source separtion algorithm.
 
-## Intended uses & limitations
-Check out a demo of the model in my 'Spaces' repository: jpdiazpardo/jpdiazpardo-whisper-tiny-metal
+More information needed
 
-Load the dataset from huggingface in your notebook:
-```python
-from transformers import WhisperForConditionalGeneration, WhisperProcessor
+## Intended uses & limitations
 
-model = WhisperForConditionalGeneration.from_pretrained("jpdiazpardo/whisper-tiny-metal")
-processor = WhisperProcessor.from_pretrained("jpdiazpardo/whisper-tiny-metal")
-```
+More information needed
 
 ## Training and evaluation data
-jpdiazpardo/guturalScream_metalVocals
+
+More information needed
 
 ## Training procedure
 
@@ -45,11 +46,19 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 1
-- training_steps: 2
+- lr_scheduler_warmup_steps: 500
+- training_steps: 4000
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss | Wer      |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.0844        | 9.62  | 1000 | 1.3967          | 104.6055 |
+| 0.0018        | 19.23 | 2000 | 1.5861          | 93.5465  |
+| 0.0008        | 28.85 | 3000 | 1.6552          | 78.9381  |
+| 0.0006        | 38.46 | 4000 | 1.6780          | 79.9061  |
+
+
 ### Framework versions
 
 - Transformers 4.32.0

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06a1457a3d01a7d27b7659401e66a38adf185ef7b0bf9a526bd768e37c867614
+oid sha256:7f1837a920b6246733d9f317b6b27f9cdb6c604823944a028e44df4b0f6a66e2
 size 151099049