GetmanY1's picture
Update README.md
7fc5bcb verified
|
raw
history blame
5.04 kB
metadata
license: apache-2.0
tags:
  - automatic-speech-recognition
  - fi
  - finnish
library_name: transformers
language: fi
base_model:
  - GetmanY1/wav2vec2-large-fi-150k
model-index:
  - name: wav2vec2-large-fi-150k-finetuned
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Lahjoita puhetta (Donate Speech)
          type: lahjoita-puhetta
          args: fi
        metrics:
          - name: Dev WER
            type: wer
            value: 15.34
          - name: Dev CER
            type: cer
            value: 4.14
          - name: Test WER
            type: wer
            value: 16.86
          - name: Test CER
            type: cer
            value: 5.07
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Finnish Parliament
          type: FinParl
          args: fi
        metrics:
          - name: Dev16 WER
            type: wer
            value: 11.3
          - name: Dev16 CER
            type: cer
            value: 4.75
          - name: Test16 WER
            type: wer
            value: 8.29
          - name: Test16 CER
            type: cer
            value: 3.34
          - name: Test20 WER
            type: wer
            value: 6.94
          - name: Test20 CER
            type: cer
            value: 2.15
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 16.1
          type: mozilla-foundation/common_voice_16_1
          args: fi
        metrics:
          - name: Dev WER
            type: wer
            value: 7.17
          - name: Dev CER
            type: cer
            value: 1.11
          - name: Test WER
            type: wer
            value: 5.86
          - name: Test CER
            type: cer
            value: 0.91
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: FLEURS
          type: google/fleurs
          args: fi_fi
        metrics:
          - name: Dev WER
            type: wer
            value: 9.2
          - name: Dev CER
            type: cer
            value: 5.23
          - name: Test WER
            type: wer
            value: 10.69
          - name: Test CER
            type: cer
            value: 5.79

Finnish Wav2vec2-Large ASR

GetmanY1/wav2vec2-large-fi-150k fine-tuned on 4600 hours of Finnish speech on 16kHz sampled speech audio:

When using the model make sure that your speech input is also sampled at 16Khz.

Model description

The Finnish Wav2Vec2 Large has the same architecture and uses the same training objective as the English and multilingual one described in Paper.

GetmanY1/wav2vec2-large-fi-150k is a large-scale, 317-million parameter monolingual model pre-trained on 158k hours of unlabeled Finnish speech, including KAVI radio and television archive materials, Lahjoita puhetta (Donate Speech), Finnish Parliament, Finnish VoxPopuli.

You can read more about the pre-trained model from this paper. The training scripts are available on GitHub.

Intended uses

You can use this model for Finnish ASR (speech-to-text).

How to use

To transcribe audio files the model can be used as a standalone acoustic model as follows:

from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
from datasets import load_dataset
import torch

# load model and processor
processor = Wav2Vec2Processor.from_pretrained("GetmanY1/wav2vec2-large-fi-150k-finetuned")
model = Wav2Vec2ForCTC.from_pretrained("GetmanY1/wav2vec2-large-fi-150k-finetuned")

# load dummy dataset and read soundfiles
ds = load_dataset("mozilla-foundation/common_voice_16_1", "fi", split='test')

# tokenize
input_values = processor(ds[0]["audio"]["array"], return_tensors="pt", padding="longest").input_values  # Batch size 1

# retrieve logits
logits = model(input_values).logits

# take argmax and decode
predicted_ids = torch.argmax(logits, dim=-1)
transcription = processor.batch_decode(predicted_ids)

Team Members

Feel free to contact us for more details 🤗