Upload TFWhisperForConditionalGeneration

README.md

@@ -14,12 +14,12 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.4418
-- Train Accuracy: 0.0305
-- Train Wermet: 6.6665
-- Validation Loss: 0.5963
-- Validation Accuracy: 0.0305
-- Validation Wermet: 4.9877
+- Train Loss: 0.4565
+- Train Accuracy: 0.0304
+- Train Wermet: 19.0749
+- Validation Loss: 0.6117
+- Validation Accuracy: 0.0304
+- Validation Wermet: 21.9796
 - Epoch: 9
 
 ## Model description
@@ -46,16 +46,16 @@ The following hyperparameters were used during training:
 
 | Train Loss | Train Accuracy | Train Wermet | Validation Loss | Validation Accuracy | Validation Wermet | Epoch |
 |:----------:|:--------------:|:------------:|:---------------:|:-------------------:|:-----------------:|:-----:|
-| 5.0901     | 0.0113         | 53.3790      | 4.4090          | 0.0122              | 42.3548           | 0     |
-| 4.3135     | 0.0127         | 42.3551      | 3.9430          | 0.0149              | 37.1045           | 1     |
-| 3.3458     | 0.0173         | 31.6069      | 2.3945          | 0.0222              | 25.5461           | 2     |
-| 1.9669     | 0.0232         | 13.7935      | 1.4966          | 0.0261              | 6.9562            | 3     |
-| 1.2830     | 0.0262         | 10.0196      | 1.1100          | 0.0279              | 9.5683            | 4     |
-| 0.9517     | 0.0278         | 8.1513       | 0.9065          | 0.0289              | 7.8180            | 5     |
-| 0.7555     | 0.0287         | 7.5457       | 0.7892          | 0.0295              | 5.1479            | 6     |
-| 0.6204     | 0.0295         | 7.0748       | 0.7025          | 0.0299              | 6.9938            | 7     |
-| 0.5202     | 0.0300         | 7.2085       | 0.6409          | 0.0303              | 7.6979            | 8     |
-| 0.4418     | 0.0305         | 6.6665       | 0.5963          | 0.0305              | 4.9877            | 9     |
+| 5.1027     | 0.0113         | 52.5530      | 4.4267          | 0.0121              | 41.4796           | 0     |
+| 4.3285     | 0.0126         | 38.6893      | 3.9835          | 0.0145              | 33.6050           | 1     |
+| 3.4573     | 0.0168         | 30.7714      | 2.5568          | 0.0215              | 31.7559           | 2     |
+| 2.0878     | 0.0226         | 20.5131      | 1.5738          | 0.0257              | 21.2159           | 3     |
+| 1.3529     | 0.0258         | 17.4367      | 1.1712          | 0.0276              | 17.7695           | 4     |
+| 0.9953     | 0.0275         | 18.7308      | 0.9389          | 0.0287              | 20.5259           | 5     |
+| 0.7852     | 0.0286         | 18.5731      | 0.8074          | 0.0294              | 17.6576           | 6     |
+| 0.6428     | 0.0293         | 18.2945      | 0.7219          | 0.0298              | 19.9850           | 7     |
+| 0.5384     | 0.0299         | 18.9258      | 0.6610          | 0.0301              | 18.9327           | 8     |
+| 0.4565     | 0.0304         | 19.0749      | 0.6117          | 0.0304              | 21.9796           | 9     |
 
 
 ### Framework versions

config.json

@@ -8,7 +8,6 @@
   ],
   "attention_dropout": 0.0,
   "begin_suppress_tokens": [
-    220,
     50257
   ],
   "bos_token_id": 50257,
@@ -24,7 +23,20 @@
   "encoder_layerdrop": 0.0,
   "encoder_layers": 4,
   "eos_token_id": 50257,
-  "forced_decoder_ids": null,
+  "forced_decoder_ids": [
+    [
+      1,
+      50289
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
   "init_std": 0.02,
   "is_encoder_decoder": true,
   "mask_feature_length": 10,

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d46e93c9de663a214900b272a35d8fba1ef0b7e6da7bbf674fd875f356c28fa
+oid sha256:a67374864f63b84b35ed5e2c4dad453b52b8e6881219687de4e9bf8202435b56
 size 151253984