tuanio/WhisperCTC

Model Card for Model ID

This modelcard aims to be a base template for new models. It has been generated using this raw template.

Model Details

Model Description

class WhisperCTC(nn.Module):
    def __init__(
        self,
        encoder_id: str = "tuanio/whisper-encoder.tiny.en",
        dropout: float = 0.1,
        vocab_size: int = 47,
    ):
        super().__init__()
        self.encoder = WhisperEncoder.from_pretrained(encoder_id)
        print("Freezing Whisper Encoder...")
        self.encoder._freeze_parameters()
        print("Freezed!")
        self.lm_head = nn.Sequential(
            nn.SiLU(),
            nn.Dropout(dropout),
            nn.Linear(self.encoder.config.d_model, vocab_size),
        )
        nn.init.kaiming_uniform_(
            self.lm_head[-1].weight, mode="fan_in", nonlinearity="relu"
        )

    def forward(self, feat: Tensor, attn_mask: Tensor):
        enc = self.encoder(
            input_features=feat, attention_mask=attn_mask
        ).last_hidden_state
        logits = self.lm_head(enc)
        log_probs = nn.functional.log_softmax(logits, dim=-1)
        return log_probs

• Developed by: [More Information Needed]
• Shared by [optional]: [More Information Needed]
• Model type: [More Information Needed]
• Language(s) (NLP): [More Information Needed]
• License: [More Information Needed]
• Finetuned from model [optional]: [More Information Needed]

Model Sources [optional]

• Repository: [More Information Needed]
• Paper [optional]: [More Information Needed]
• Demo [optional]: [More Information Needed]

Uses

Direct Use

[More Information Needed]

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

• IndictTTS: https://www.kaggle.com/datasets/tuannguyenvananh/indictts-english

[More Information Needed]

Training Procedure

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

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]

[More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

• Hardware Type: [More Information Needed]
• Hours used: [More Information Needed]
• Cloud Provider: [More Information Needed]
• Compute Region: [More Information Needed]
• Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]