Model save

README.md

@@ -1,7 +1,5 @@
 ---
 library_name: transformers
-language:
-- spa
 license: apache-2.0
 base_model: openai/whisper-tiny
 tags:
@@ -9,19 +7,19 @@ tags:
 metrics:
 - wer
 model-index:
-- name: Whisper Tiny Few Audios - vfranchis
+- name: whisper-tiny-few-audios
   results: []
 ---
 
 <!-- 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 Few Audios - vfranchis
+# whisper-tiny-few-audios
 
-This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Few audios 1.0 dataset.
+This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the None dataset.
 It achieves the following results on the evaluation set:
 - Loss: nan
-- Wer: 1300.0
+- Wer: 88.8889
 
 ## Model description
 
@@ -41,11 +39,9 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 8
+- train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 10
@@ -54,18 +50,18 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch   | Step | Validation Loss | Wer    |
-|:-------------:|:-------:|:----:|:---------------:|:------:|
-| 0.0           | 2.8571  | 10   | nan             | 1300.0 |
-| 0.0           | 5.7143  | 20   | nan             | 1300.0 |
-| 0.0           | 8.5714  | 30   | nan             | 1300.0 |
-| 0.0           | 11.4286 | 40   | nan             | 1300.0 |
-| 0.0           | 14.2857 | 50   | nan             | 1300.0 |
-| 0.0           | 17.1429 | 60   | nan             | 1300.0 |
-| 0.0           | 20.0    | 70   | nan             | 1300.0 |
-| 0.0           | 22.8571 | 80   | nan             | 1300.0 |
-| 0.0           | 25.7143 | 90   | nan             | 1300.0 |
-| 0.0           | 28.5714 | 100  | nan             | 1300.0 |
+| Training Loss | Epoch | Step | Validation Loss | Wer     |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|
+| 0.0           | 2.5   | 10   | nan             | 88.8889 |
+| 0.0           | 5.0   | 20   | nan             | 88.8889 |
+| 0.0           | 7.5   | 30   | nan             | 88.8889 |
+| 0.0           | 10.0  | 40   | nan             | 88.8889 |
+| 0.0           | 12.5  | 50   | nan             | 88.8889 |
+| 0.0           | 15.0  | 60   | nan             | 88.8889 |
+| 0.0           | 17.5  | 70   | nan             | 88.8889 |
+| 0.0           | 20.0  | 80   | nan             | 88.8889 |
+| 0.0           | 22.5  | 90   | nan             | 88.8889 |
+| 0.0           | 25.0  | 100  | nan             | 88.8889 |
 
 
 ### Framework versions

generation_config.json

@@ -32,6 +32,16 @@
   "bos_token_id": 50257,
   "decoder_start_token_id": 50258,
   "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      null
+    ],
+    [
+      2,
+      50359
+    ]
+  ],
   "is_multilingual": true,
   "lang_to_id": {
     "<|af|>": 50327,