Training in progress, step 500

README.md

@@ -1,40 +1,23 @@
 ---
+language:
+- dv
 license: apache-2.0
-base_model: openai/whisper-tiny
+base_model: openai/whisper-small
 tags:
 - generated_from_trainer
 datasets:
-- PolyAI/minds14
-metrics:
-- wer
+- mozilla-foundation/common_voice_13_0
 model-index:
-- name: whisper-small-dv
-  results:
-  - task:
-      name: Automatic Speech Recognition
-      type: automatic-speech-recognition
-    dataset:
-      name: PolyAI/minds14
-      type: PolyAI/minds14
-      config: en-US
-      split: train
-      args: en-US
-    metrics:
-    - name: Wer
-      type: wer
-      value: 0.0
+- name: Whisper Small Dv
+  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-small-dv
+# Whisper Small Dv
 
-This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.0000
-- Wer Ortho: 0.0
-- Wer: 0.0
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 13 dataset.
 
 ## Model description
 
@@ -60,14 +43,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant_with_warmup
 - lr_scheduler_warmup_steps: 50
-- training_steps: 50
-
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
-|:-------------:|:-----:|:----:|:---------------:|:---------:|:---:|
-| 0.0           | 1.79  | 50   | 0.0000          | 0.0       | 0.0 |
-
+- training_steps: 500
 
 ### Framework versions
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "CordwainerSmith/whisper-tiny-PolyAI-minds14",
+  "_name_or_path": "sanchit-gandhi/whisper-small-dv",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,
@@ -13,17 +13,17 @@
   ],
   "bos_token_id": 50257,
   "classifier_proj_size": 256,
-  "d_model": 384,
-  "decoder_attention_heads": 6,
-  "decoder_ffn_dim": 1536,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 4,
+  "decoder_layers": 12,
   "decoder_start_token_id": 50258,
   "dropout": 0.0,
-  "encoder_attention_heads": 6,
-  "encoder_ffn_dim": 1536,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
   "encoder_layerdrop": 0.0,
-  "encoder_layers": 4,
+  "encoder_layers": 12,
   "eos_token_id": 50257,
   "forced_decoder_ids": [
     [
@@ -52,7 +52,7 @@
   "max_target_positions": 448,
   "median_filter_width": 7,
   "model_type": "whisper",
-  "num_hidden_layers": 4,
+  "num_hidden_layers": 12,
   "num_mel_bins": 80,
   "pad_token_id": 50257,
   "scale_embedding": false,
@@ -140,8 +140,6 @@
     49870,
     50254,
     50258,
-    50358,
-    50359,
     50360,
     50361,
     50362

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8bd1112ab6515cbdea9590ae1dcfeaa4840dbb67e622df77bf382238a5b88ae
-size 151099049
+oid sha256:1f99c86b534ca911d9e4bbeafca9617d07cba0de1f06dafd069db00c5ae222fc
+size 967102729

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21b047d135c1ffae4b14b50622c87ebab8ce4e795df4b97fc0328c7e0f38ff37
+oid sha256:71cf6cca35c37866adfa57f660b0cda218a99db43945d1e9c1caaac5b4cf87be
 size 4219