End of training

README.md

@@ -1,11 +1,7 @@
 ---
 library_name: transformers
-license: apache-2.0
-base_model: openai/whisper-small
 tags:
 - generated_from_trainer
-metrics:
-- bleu
 model-index:
 - name: whisper-small-es-ja
   results: []
@@ -16,10 +12,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 # whisper-small-es-ja
 
-This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset.
+This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1884
-- Bleu: 19.9880
+- eval_loss: 8.4164
+- eval_bleu: 21.5256
+- eval_runtime: 210.1767
+- eval_samples_per_second: 6.499
+- eval_steps_per_second: 0.409
+- step: 0
 
 ## Model description
 
@@ -39,30 +39,14 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 16
-- eval_batch_size: 8
+- train_batch_size: 32
+- eval_batch_size: 16
 - seed: 42
-- distributed_type: multi-GPU
-- num_devices: 2
-- total_train_batch_size: 32
-- total_eval_batch_size: 16
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- training_steps: 1500
+- training_steps: 5000
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch  | Step | Validation Loss | Bleu    |
-|:-------------:|:------:|:----:|:---------------:|:-------:|
-| 1.4562        | 0.7911 | 250  | 1.4257          | 13.1050 |
-| 1.1315        | 1.5823 | 500  | 1.2744          | 16.8159 |
-| 0.9172        | 2.3734 | 750  | 1.2167          | 18.6278 |
-| 0.7598        | 3.1646 | 1000 | 1.1958          | 20.1775 |
-| 0.7627        | 3.9557 | 1250 | 1.1817          | 20.0966 |
-| 0.6803        | 4.7468 | 1500 | 1.1884          | 19.9880 |
-
-
 ### Framework versions
 
 - Transformers 4.47.1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/whisper-small",
+  "_name_or_path": "/home/magonzalez/Projects/stt/whisper-small-es-ja/checkpoint-2500",
   "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:e4fa84473fdf2b3bf08e35fdb21e6944ed801e566f971d5d5992bb4580d5189e
+oid sha256:d84079b162ff63f83a8d0a2235a99685695a2b593908db1a2796b85e8b228b0a
 size 966995080

runs/Dec19_15-34-41_mad-loc-analytics3/events.out.tfevents.1734618882.mad-loc-analytics3.925440.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cadf5f3a98054d4e37bd9b6e93b755e9e86605a9ec00380fd945267ca34d573
-size 23327
+oid sha256:6a076a542710913ac75506ac89f5f4b2879fe9fa823196c2f9d5f4a78cc946f3
+size 24701

runs/Dec19_17-27-47_mad-loc-analytics3/events.out.tfevents.1734625909.mad-loc-analytics3.975886.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f51bb86c2f7dcae06950f7c893fc798fa351744b58256beff63dc2e6c720411e
+size 342

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc52069a4e1640d31f048bde228c61326895f0786ba7055c5552b62815f28e4a
+oid sha256:cdeaeeb5002bc0df20ebfaf11471dd5136e7ddbf859506b3569e0e3f78089254
 size 5496