End of training

README.md

@@ -1,42 +1,40 @@
 ---
-language:
-- en
 license: apache-2.0
 base_model: openai/whisper-tiny
 tags:
 - generated_from_trainer
 datasets:
-- mozilla-foundation/common_voice_13_0
+- PolyAI/minds14
 metrics:
 - wer
 model-index:
-- name: Whisper Tiny En - Ariel Cerda
+- name: whisper-tiny-en
   results:
   - task:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: Common Voice 13
-      type: mozilla-foundation/common_voice_13_0
-      config: dv
-      split: test
-      args: dv
+      name: PolyAI/minds14
+      type: PolyAI/minds14
+      config: en-US
+      split: train
+      args: en-US
     metrics:
     - name: Wer
       type: wer
-      value: 87.81340195430678
+      value: 32.99881936245573
 ---
 
 <!-- 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 Tiny En - Ariel Cerda
+# whisper-tiny-en
 
-This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Common Voice 13 dataset.
+This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9528
-- Wer Ortho: 138.6030
-- Wer: 87.8134
+- Loss: 0.8597
+- Wer Ortho: 32.7576
+- Wer: 32.9988
 
 ## Model description
 
@@ -62,14 +60,21 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant_with_warmup
 - lr_scheduler_warmup_steps: 50
-- training_steps: 500
+- training_steps: 4000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Wer Ortho | Wer     |
-|:-------------:|:------:|:----:|:---------------:|:---------:|:-------:|
-| 0.9417        | 1.6287 | 500  | 0.9528          | 138.6030  | 87.8134 |
+| Training Loss | Epoch    | Step | Validation Loss | Wer Ortho | Wer     |
+|:-------------:|:--------:|:----:|:---------------:|:---------:|:-------:|
+| 0.0007        | 17.2414  | 500  | 0.6479          | 32.3874   | 32.3495 |
+| 0.0002        | 34.4828  | 1000 | 0.7071          | 32.8809   | 32.9988 |
+| 0.0001        | 51.7241  | 1500 | 0.7428          | 32.7576   | 32.9988 |
+| 0.0001        | 68.9655  | 2000 | 0.7709          | 32.6959   | 32.9398 |
+| 0.0           | 86.2069  | 2500 | 0.7948          | 32.7576   | 33.0579 |
+| 0.0           | 103.4483 | 3000 | 0.8179          | 33.0043   | 33.2349 |
+| 0.0           | 120.6897 | 3500 | 0.8392          | 32.9426   | 33.1759 |
+| 0.0           | 137.9310 | 4000 | 0.8597          | 32.7576   | 32.9988 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2861b898ea1ede54d5d6ad11fc6a12f1e01992f606cee1cb487a758f6b06524e
+oid sha256:79933f495fc073ab818db26fc83ab56b469542730a4b4ba61fb0b658d18da78e
 size 151061672