Instructions to use alakxender/whisper-large-v3-cv17-dv with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use alakxender/whisper-large-v3-cv17-dv with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="alakxender/whisper-large-v3-cv17-dv")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("alakxender/whisper-large-v3-cv17-dv") model = AutoModelForSpeechSeq2Seq.from_pretrained("alakxender/whisper-large-v3-cv17-dv") - Notebooks
- Google Colab
- Kaggle
Commit ·
41aadb6
1
Parent(s): 0d6913d
Training in progress, step 3000, checkpoint
Browse files
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 71.37931034482759,
|
| 3 |
"best_model_checkpoint": "./whisper-large-v3-cv17-dv/checkpoint-2700",
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 300,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -277,6 +277,36 @@
|
|
| 277 |
"eval_steps_per_second": 0.02,
|
| 278 |
"eval_wer": 71.37931034482759,
|
| 279 |
"step": 2700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 280 |
}
|
| 281 |
],
|
| 282 |
"logging_steps": 100,
|
|
@@ -296,7 +326,7 @@
|
|
| 296 |
"attributes": {}
|
| 297 |
}
|
| 298 |
},
|
| 299 |
-
"total_flos": 1.
|
| 300 |
"train_batch_size": 16,
|
| 301 |
"trial_name": null,
|
| 302 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 71.37931034482759,
|
| 3 |
"best_model_checkpoint": "./whisper-large-v3-cv17-dv/checkpoint-2700",
|
| 4 |
+
"epoch": 8.931596091205211,
|
| 5 |
"eval_steps": 300,
|
| 6 |
+
"global_step": 3000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 277 |
"eval_steps_per_second": 0.02,
|
| 278 |
"eval_wer": 71.37931034482759,
|
| 279 |
"step": 2700
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 8.280130293159608,
|
| 283 |
+
"grad_norm": 0.5797841548919678,
|
| 284 |
+
"learning_rate": 3.4428571428571434e-06,
|
| 285 |
+
"loss": 0.0079,
|
| 286 |
+
"step": 2800
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 8.60586319218241,
|
| 290 |
+
"grad_norm": 0.5921549797058105,
|
| 291 |
+
"learning_rate": 3.1571428571428573e-06,
|
| 292 |
+
"loss": 0.0068,
|
| 293 |
+
"step": 2900
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 8.931596091205211,
|
| 297 |
+
"grad_norm": 0.7851368188858032,
|
| 298 |
+
"learning_rate": 2.8714285714285717e-06,
|
| 299 |
+
"loss": 0.0067,
|
| 300 |
+
"step": 3000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 8.931596091205211,
|
| 304 |
+
"eval_loss": 0.39471304416656494,
|
| 305 |
+
"eval_runtime": 145.8938,
|
| 306 |
+
"eval_samples_per_second": 0.685,
|
| 307 |
+
"eval_steps_per_second": 0.021,
|
| 308 |
+
"eval_wer": 71.72413793103448,
|
| 309 |
+
"step": 3000
|
| 310 |
}
|
| 311 |
],
|
| 312 |
"logging_steps": 100,
|
|
|
|
| 326 |
"attributes": {}
|
| 327 |
}
|
| 328 |
},
|
| 329 |
+
"total_flos": 1.62910043799552e+20,
|
| 330 |
"train_batch_size": 16,
|
| 331 |
"trial_name": null,
|
| 332 |
"trial_params": null
|