README.md

metadata

language:
  - ro
license: apache-2.0
tags:
  - whisper-event
pinned: true
datasets:
  - mozilla-foundation/common_voice_11_0
  - gigant/romanian_speech_synthesis_0_8_1
model-index:
  - name: Whisper Medium Romanian
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: mozilla-foundation/common_voice_11_0 ro
          type: mozilla-foundation/common_voice_11_0
          config: ro
          split: test
          args: ro
        metrics:
          - name: Wer
            type: wer
            value: 4.73
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: google/fleurs ro
          type: google/fleurs
          config: ro
          split: test
          args: ro
        metrics:
          - name: Wer
            type: wer
            value: 19.64
metrics:
  - wer

Whisper Medium Romanian

This model is a fine-tuned version of openai/whisper-medium on the Common Voice 11.0 dataset, and the Romanian speech synthesis corpus. It achieves the following results on the evaluation set:

• eval_loss: 0.06453
• eval_wer: 4.717
• epoch: 7.03
• step: 3500

Model description

The architecture is the same as openai/whisper-medium.

Training and evaluation data

The model was trained on the Common Voice 11.0 dataset (train+validation+other splits) and the Romanian speech synthesis corpus, and was tested on the test split of the Common Voice 11.0 dataset.

Usage

Inference with 🤗 transformers

from transformers import WhisperProcessor, WhisperForConditionalGeneration
from datasets import Audio, load_dataset
import torch

# load model and processor
processor = WhisperProcessor.from_pretrained("gigant/whisper-medium-romanian")
model = WhisperForConditionalGeneration.from_pretrained("gigant/whisper-medium-romanian")

# load dummy dataset and read soundfiles
ds = load_dataset("common_voice", "ro", split="test", streaming=True)
ds = ds.cast_column("audio", Audio(sampling_rate=16_000))
input_speech = next(iter(ds))["audio"]["array"]
model.config.forced_decoder_ids = processor.get_decoder_prompt_ids(language = "ro", task = "transcribe")
input_features = processor(input_speech, return_tensors="pt", sampling_rate=16_000).input_features 
predicted_ids = model.generate(input_features, max_length=448)
# transcription = processor.batch_decode(predicted_ids)
transcription = processor.batch_decode(predicted_ids, skip_special_tokens = True)

The code was adapted from openai/whisper-medium.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 5000
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.0+cu117
• Datasets 2.7.1.dev0
• Tokenizers 0.13.2