End of training

README.md

@@ -1,27 +1,25 @@
 ---
 library_name: transformers
-language:
-- spa
 license: apache-2.0
-base_model: stinoco/whisper-tiny-clinical-assistance
+base_model: rasel35/whisper-base-es-medical-terms
 tags:
 - generated_from_trainer
 metrics:
 - wer
 model-index:
-- name: Whisper Pre Tuned 300 Audios - Nacho v1.1
+- name: whisper-tiny-300-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 Pre Tuned 300 Audios - Nacho v1.1
+# whisper-tiny-300-audios
 
-This model is a fine-tuned version of [stinoco/whisper-tiny-clinical-assistance](https://huggingface.co/stinoco/whisper-tiny-clinical-assistance) on the 300 audios 1.0 dataset.
+This model is a fine-tuned version of [rasel35/whisper-base-es-medical-terms](https://huggingface.co/rasel35/whisper-base-es-medical-terms) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4287
-- Wer: 22.0273
+- Loss: 0.4543
+- Wer: 19.9630
 
 ## Model description
 
@@ -56,16 +54,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:-------:|
-| 1.9264        | 1.0    | 18   | 1.1710          | 43.2749 |
-| 0.7775        | 2.0    | 36   | 0.5345          | 31.3840 |
-| 0.3526        | 3.0    | 54   | 0.4953          | 50.0975 |
-| 0.1628        | 4.0    | 72   | 0.4611          | 25.1462 |
-| 0.0932        | 5.0    | 90   | 0.4517          | 22.2222 |
-| 0.0559        | 6.0    | 108  | 0.4196          | 21.0526 |
-| 0.0359        | 7.0    | 126  | 0.4440          | 22.4172 |
-| 0.0224        | 8.0    | 144  | 0.4335          | 23.1969 |
-| 0.0175        | 9.0    | 162  | 0.4301          | 21.8324 |
-| 0.0051        | 9.4507 | 170  | 0.4287          | 22.0273 |
+| 1.8385        | 1.0    | 18   | 1.1087          | 37.7079 |
+| 0.6509        | 2.0    | 36   | 0.5255          | 25.1386 |
+| 0.2616        | 3.0    | 54   | 0.4827          | 21.2569 |
+| 0.1177        | 4.0    | 72   | 0.4747          | 21.0721 |
+| 0.0719        | 5.0    | 90   | 0.4630          | 20.8872 |
+| 0.0391        | 6.0    | 108  | 0.4802          | 21.8115 |
+| 0.0313        | 7.0    | 126  | 0.4613          | 20.7024 |
+| 0.023         | 8.0    | 144  | 0.4557          | 17.7449 |
+| 0.0104        | 9.0    | 162  | 0.4513          | 20.1479 |
+| 0.0042        | 9.4507 | 170  | 0.4543          | 19.9630 |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "stinoco/whisper-tiny-clinical-assistance",
+  "_name_or_path": "rasel35/whisper-base-es-medical-terms",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,
@@ -10,19 +10,32 @@
   "begin_suppress_tokens": null,
   "bos_token_id": 50257,
   "classifier_proj_size": 256,
-  "d_model": 384,
-  "decoder_attention_heads": 6,
-  "decoder_ffn_dim": 1536,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 4,
+  "decoder_layers": 6,
   "decoder_start_token_id": 50258,
   "dropout": 0.0,
-  "encoder_attention_heads": 6,
-  "encoder_ffn_dim": 1536,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
   "encoder_layerdrop": 0.0,
-  "encoder_layers": 4,
+  "encoder_layers": 6,
   "eos_token_id": 50257,
-  "forced_decoder_ids": null,
+  "forced_decoder_ids": [
+    [
+      1,
+      50259
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
   "init_std": 0.02,
   "is_encoder_decoder": true,
   "mask_feature_length": 10,
@@ -36,7 +49,7 @@
   "max_target_positions": 448,
   "median_filter_width": 7,
   "model_type": "whisper",
-  "num_hidden_layers": 4,
+  "num_hidden_layers": 6,
   "num_mel_bins": 80,
   "pad_token_id": 50257,
   "scale_embedding": false,

generation_config.json

@@ -1,28 +1,36 @@
 {
   "alignment_heads": [
-    [
-      2,
-      2
-    ],
     [
       3,
-      0
+      1
     ],
     [
-      3,
+      4,
       2
     ],
     [
-      3,
+      4,
       3
     ],
     [
-      3,
+      4,
+      7
+    ],
+    [
+      5,
+      1
+    ],
+    [
+      5,
+      2
+    ],
+    [
+      5,
       4
     ],
     [
-      3,
-      5
+      5,
+      6
     ]
   ],
   "begin_suppress_tokens": [
@@ -141,7 +149,96 @@
   "pad_token_id": 50257,
   "prev_sot_token_id": 50361,
   "return_timestamps": false,
-  "suppress_tokens": [],
+  "suppress_tokens": [
+    1,
+    2,
+    7,
+    8,
+    9,
+    10,
+    14,
+    25,
+    26,
+    27,
+    28,
+    29,
+    31,
+    58,
+    59,
+    60,
+    61,
+    62,
+    63,
+    90,
+    91,
+    92,
+    93,
+    359,
+    503,
+    522,
+    542,
+    873,
+    893,
+    902,
+    918,
+    922,
+    931,
+    1350,
+    1853,
+    1982,
+    2460,
+    2627,
+    3246,
+    3253,
+    3268,
+    3536,
+    3846,
+    3961,
+    4183,
+    4667,
+    6585,
+    6647,
+    7273,
+    9061,
+    9383,
+    10428,
+    10929,
+    11938,
+    12033,
+    12331,
+    12562,
+    13793,
+    14157,
+    14635,
+    15265,
+    15618,
+    16553,
+    16604,
+    18362,
+    18956,
+    20075,
+    21675,
+    22520,
+    26130,
+    26161,
+    26435,
+    28279,
+    29464,
+    31650,
+    32302,
+    32470,
+    36865,
+    42863,
+    47425,
+    49870,
+    50254,
+    50258,
+    50358,
+    50359,
+    50360,
+    50361,
+    50362
+  ],
   "task": "transcribe",
   "task_to_id": {
     "transcribe": 50359,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c069ec4c9e1f73237fab3c012fac58422bc3544d4dd35f9894e82b031e41bc4a
-size 151061672
+oid sha256:6bffab982321fa722ac591f630f527a6a70ac8b338c4d5b533ce0c2d7a74f2ea
+size 290403936

runs/Feb07_15-54-37_pop-os/events.out.tfevents.1738954868.pop-os.74078.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9de5b1302eaea13a303417390b36d04f4df2cbb8b067312e16b6cadb72107c13
+size 11535

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af780fe109268d0b43e272f2f2b7fda36a030d60e9816ab3e124c07a73043f6a
+oid sha256:a70c67b6d91835a8367fcd0fe2a9da3bcc8bdf85d21437245380641deaabf86a
 size 5496