33d4cdefdfe5a65f442f0e42bc45d33d6627d35ca6548d7254f191626170f210

README.md

@@ -0,0 +1,80 @@
+---
+license: apache-2.0
+base_model: openai/whisper-large-v3
+tags:
+- generated_from_trainer
+datasets:
+- mozilla-foundation/common_voice_16_0
+metrics:
+- wer
+model-index:
+- name: whisper-large-v3-pt-cv16-cuda
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: mozilla-foundation/common_voice_16_0 pt
+      type: mozilla-foundation/common_voice_16_0
+      split: None
+      args: pt
+    metrics:
+    - name: Wer
+      type: wer
+      value: 0.9998545572074984
+---
+
+<!-- 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-large-v3-pt-cv16-cuda
+
+This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the mozilla-foundation/common_voice_16_0 pt dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1325
+- Wer: 0.9999
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-06
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 2000
+- training_steps: 5000
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.199         | 0.26  | 1000 | 0.1563          | 0.1124 |
+| 0.1654        | 0.52  | 2000 | 0.1500          | 0.1052 |
+| 0.1794        | 0.77  | 3000 | 0.1379          | 0.0997 |
+| 0.0821        | 1.03  | 4000 | 0.1321          | 1.0007 |
+| 0.1292        | 1.29  | 5000 | 0.1325          | 0.9999 |
+
+
+### Framework versions
+
+- Transformers 4.37.0.dev0
+- Pytorch 2.2.0.dev20231212
+- Datasets 2.15.1.dev0
+- Tokenizers 0.15.0

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c6b0edf383dba5a20a86c58366da587af2b11f57f3238809e22174428275ba2
+oid sha256:0a3553cfea4d55a22ddc4554e797d5f41b8d4ec64eff37633af911cf87725f80
 size 1180663192

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.29,
+    "train_loss": 0.05041759390830994,
+    "train_runtime": 1177508.0135,
+    "train_samples": 30998,
+    "train_samples_per_second": 0.034,
+    "train_steps_per_second": 0.004
+}

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.032258064516129,
+  "epoch": 1.2903225806451613,
   "eval_steps": 1000,
-  "global_step": 4000,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1003,6 +1003,264 @@
       "eval_steps_per_second": 0.006,
       "eval_wer": 1.000743374272786,
       "step": 4000
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 3.263333333333333e-07,
+      "loss": 0.1092,
+      "step": 4025
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 3.18e-07,
+      "loss": 0.0928,
+      "step": 4050
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 3.096666666666666e-07,
+      "loss": 0.1481,
+      "step": 4075
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 3.0133333333333333e-07,
+      "loss": 0.1043,
+      "step": 4100
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 2.93e-07,
+      "loss": 0.1018,
+      "step": 4125
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 2.8466666666666665e-07,
+      "loss": 0.104,
+      "step": 4150
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 2.763333333333333e-07,
+      "loss": 0.1394,
+      "step": 4175
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 2.68e-07,
+      "loss": 0.0962,
+      "step": 4200
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 2.596666666666666e-07,
+      "loss": 0.1058,
+      "step": 4225
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 2.5133333333333333e-07,
+      "loss": 0.0837,
+      "step": 4250
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 2.43e-07,
+      "loss": 0.1396,
+      "step": 4275
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 2.3466666666666665e-07,
+      "loss": 0.1005,
+      "step": 4300
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 2.263333333333333e-07,
+      "loss": 0.131,
+      "step": 4325
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 2.18e-07,
+      "loss": 0.1069,
+      "step": 4350
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 2.0966666666666665e-07,
+      "loss": 0.136,
+      "step": 4375
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 2.0133333333333334e-07,
+      "loss": 0.0954,
+      "step": 4400
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.93e-07,
+      "loss": 0.1276,
+      "step": 4425
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.8466666666666665e-07,
+      "loss": 0.1033,
+      "step": 4450
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.7633333333333334e-07,
+      "loss": 0.1547,
+      "step": 4475
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.68e-07,
+      "loss": 0.1093,
+      "step": 4500
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.5966666666666668e-07,
+      "loss": 0.1435,
+      "step": 4525
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.513333333333333e-07,
+      "loss": 0.1085,
+      "step": 4550
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.4299999999999997e-07,
+      "loss": 0.1105,
+      "step": 4575
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.3466666666666665e-07,
+      "loss": 0.0858,
+      "step": 4600
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.263333333333333e-07,
+      "loss": 0.1336,
+      "step": 4625
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.1799999999999998e-07,
+      "loss": 0.0857,
+      "step": 4650
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.0966666666666666e-07,
+      "loss": 0.1146,
+      "step": 4675
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.0133333333333333e-07,
+      "loss": 0.097,
+      "step": 4700
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 9.3e-08,
+      "loss": 0.1146,
+      "step": 4725
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 8.466666666666667e-08,
+      "loss": 0.0932,
+      "step": 4750
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 7.633333333333333e-08,
+      "loss": 0.1245,
+      "step": 4775
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 6.8e-08,
+      "loss": 0.0978,
+      "step": 4800
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 5.966666666666666e-08,
+      "loss": 0.1283,
+      "step": 4825
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 5.133333333333333e-08,
+      "loss": 0.1091,
+      "step": 4850
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 4.2999999999999995e-08,
+      "loss": 0.1106,
+      "step": 4875
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 3.4666666666666666e-08,
+      "loss": 0.1131,
+      "step": 4900
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 2.633333333333333e-08,
+      "loss": 0.1219,
+      "step": 4925
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.8e-08,
+      "loss": 0.1205,
+      "step": 4950
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 9.666666666666667e-09,
+      "loss": 0.1408,
+      "step": 4975
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.3333333333333333e-09,
+      "loss": 0.1292,
+      "step": 5000
+    },
+    {
+      "epoch": 1.29,
+      "eval_loss": 0.132488414645195,
+      "eval_runtime": 160662.2084,
+      "eval_samples_per_second": 0.059,
+      "eval_steps_per_second": 0.007,
+      "eval_wer": 0.9998545572074984,
+      "step": 5000
+    },
+    {
+      "epoch": 1.29,
+      "step": 5000,
+      "total_flos": 1.3589313726578688e+20,
+      "train_loss": 0.05041759390830994,
+      "train_runtime": 1177508.0135,
+      "train_samples_per_second": 0.034,
+      "train_steps_per_second": 0.004
     }
   ],
   "logging_steps": 25,
@@ -1010,7 +1268,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 1000,
-  "total_flos": 1.0871315081330688e+20,
+  "total_flos": 1.3589313726578688e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null