Model save

README.md

@@ -1,42 +1,39 @@
 ---
-language:
-- gl
 license: apache-2.0
 base_model: openai/whisper-base
 tags:
-- whisper-event
 - generated_from_trainer
 datasets:
-- mozilla-foundation/common_voice_13_0
+- common_voice_13_0
 metrics:
 - wer
 model-index:
-- name: Whisper Base Galician
+- name: openai/whisper-base
   results:
   - task:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: mozilla-foundation/common_voice_13_0 gl
-      type: mozilla-foundation/common_voice_13_0
+      name: common_voice_13_0
+      type: common_voice_13_0
       config: gl
       split: test
       args: gl
     metrics:
     - name: Wer
       type: wer
-      value: 18.687913907284766
+      value: 17.290976821192054
 ---
 
 <!-- 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 Base Galician
+# openai/whisper-base
 
-This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the mozilla-foundation/common_voice_13_0 gl dataset.
+This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the common_voice_13_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4754
-- Wer: 18.6879
+- Loss: 0.4360
+- Wer: 17.2910
 
 ## Model description
 
@@ -63,21 +60,22 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
 - training_steps: 5000
+- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.0088        | 9.02  | 1000 | 0.4219          | 18.7776 |
-| 0.0015        | 19.02 | 2000 | 0.4754          | 18.6879 |
-| 0.0008        | 29.02 | 3000 | 0.5036          | 18.9000 |
-| 0.0005        | 39.02 | 4000 | 0.5225          | 19.0553 |
-| 0.0004        | 49.02 | 5000 | 0.5307          | 19.1122 |
+| 0.372         | 10.0  | 1000 | 0.4173          | 21.0023 |
+| 0.1352        | 20.0  | 2000 | 0.3982          | 18.3620 |
+| 0.0638        | 30.0  | 3000 | 0.4175          | 17.8842 |
+| 0.0371        | 40.0  | 4000 | 0.4310          | 17.4721 |
+| 0.0279        | 50.0  | 5000 | 0.4360          | 17.2910 |
 
 
 ### Framework versions
 
-- Transformers 4.33.0.dev0
-- Pytorch 2.0.1+cu117
-- Datasets 2.14.4
-- Tokenizers 0.13.3
+- Transformers 4.37.2
+- Pytorch 2.2.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

generation_config.json

@@ -152,10 +152,11 @@
     "<|yo|>": 50325,
     "<|zh|>": 50260
   },
-  "max_initial_timestamp_index": 1,
+  "max_initial_timestamp_index": 50,
   "max_length": 448,
   "no_timestamps_token_id": 50363,
   "pad_token_id": 50257,
+  "prev_sot_token_id": 50361,
   "return_timestamps": false,
   "suppress_tokens": [
     1,
@@ -251,5 +252,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.33.0.dev0"
+  "transformers_version": "4.37.2"
 }