Update README.md

README.md

@@ -108,7 +108,7 @@ Use the code below to get started with the model.
 
 ### Training Data
 
-<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+- IndictTTS: https://www.kaggle.com/datasets/tuannguyenvananh/indictts-english
 
 [More Information Needed]
 
@@ -123,8 +123,74 @@ Use the code below to get started with the model.
 
 #### Training Hyperparameters
 
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
+```yaml
+data_cfg:
+  dataset:
+    processor:
+      feat_extractor_id: ${model_cfg.model.encoder_id}
+      tokenizer_id: ${model_cfg.tokenizer_id}
+    path:
+      base:
+        indict_tts: ../IndicTTS
+        cv: ../
+      train:
+        - train_data/indict_tts_train.jsonl
+        # - train_data/cv_train.jsonl
+      test:
+        - train_data/indict_tts_test.jsonl
+        # - train_data/cv_test.jsonl
+      dev:
+        - train_data/indict_tts_dev.jsonl
+        # - train_data/cv_dev.jsonl
+  dataloader:
+    batch_size: 46
+    num_workers: 8
+    pin_memory: True
+
+model_cfg:
+  tokenizer_id: tuanio/wav2vec2-phoneme-ipa-ctc
+  model:
+    dropout: 0.1
+    encoder_id: tuanio/whisper-encoder.medium.en
+  optim:
+    lr: 1.25e-05
+    betas: [0.9, 0.998]
+    weight_decay: 0.01
+  scheduler:
+    name: linear
+    total_steps: -1
+    warmup_ratio: 0.05
+    interval: step
+    frequency: 1
+
+trainer_cfg:
+  log:
+    wandb: True
+  logger_wandb:
+    project: aped_indian-lish
+    name: whisper-medium-indict-tts-only-from-epoch1
+    log_model: all
+  arguments:
+    accelerator: gpu
+    devices: -1
+    max_epochs: 10
+    log_every_n_steps: 1
+    enable_checkpointing: True
+    accumulate_grad_batches: 2
+    inference_mode: True
+    gradient_clip_val: 5.0
+    check_val_every_n_epoch: 1
+    val_check_interval: null
+
+
+experiment_cfg:
+  train: True
+  valid: True
+  test: True
+  ckpt:
+    resume_ckpt: True
+    ckpt_path: ckpt/medium.epoch3.ckpt
+```
 #### Speeds, Sizes, Times [optional]
 
 <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->