Wav2vec2 Xlsr 1b Finnish Lm

🚀 Wav2Vec2 XLS-R for Finnish ASR

This acoustic model is a fine - tuned version of facebook/wav2vec2-xls-r-1b for Finnish Automatic Speech Recognition (ASR). It offers high - quality speech recognition capabilities for the Finnish language.

🚀 Quick Start

This acoustic model is a fine - tuned version of facebook/wav2vec2-xls-r-1b for Finnish ASR. The model has been fine - tuned with 259.57 hours of Finnish transcribed speech data.

This repository also includes a Finnish KenLM language model used in the decoding phase with the acoustic model.

Note: this model is exactly the same as the Finnish - NLP/wav2vec2-xlsr-1b-finnish-lm model, so it has just been copied/moved to the Finnish - NLP Hugging Face organization.

Note: there is a better V2 version of this model which has been fine - tuned longer with 16 hours of more data: Finnish - NLP/wav2vec2-xlsr-1b-finnish-lm-v2

✨ Features

• Fine - tuned for Finnish: Specifically adapted for Finnish ASR using a large amount of Finnish transcribed speech data.
• Language Model Integration: Includes a Finnish KenLM language model for the decoding phase.

📚 Documentation

Model description

Wav2Vec2 XLS - R is Facebook AI's large - scale multilingual pretrained model for speech. It is pretrained on 436k hours of unlabeled speech, including VoxPopuli, MLS, CommonVoice, BABEL, and VoxLingua107. It uses the wav2vec 2.0 objective, in 128 languages.

You can read more about the pretrained model from [this blog](https://ai.facebook.com/blog/xls-r-self - supervised - speech - processing - for - 128 - languages) and this paper.

This model is a fine - tuned version of the pretrained model (1 billion parameter variant) for Finnish ASR.

Intended uses & limitations

How to use

Check the [run - finnish - asr - models.ipynb](https://huggingface.co/aapot/wav2vec2-xlsr-1b-finnish-lm/blob/main/run - finnish - asr - models.ipynb) notebook in this repository for a detailed example on how to use this model.

Limitations and bias

⚠️ Important Note

This model was fine - tuned with audio samples which maximum length was 20 seconds, so this model most likely works the best for quite short audios of similar length. However, you can try this model with a lot longer audios too and see how it works. If you encounter out of memory errors with very long audio files, you can use the audio chunking method introduced in [this blog post](https://huggingface.co/blog/asr - chunking).

A vast majority of the data used for fine - tuning was from the Finnish Parliament dataset, so this model may not generalize so well to very different domains like common daily spoken Finnish with dialects etc. In addition, audios of the datasets tend to be adult male dominated, so this model may not work as well for speeches of children and women, for example.

The Finnish KenLM language model used in the decoding phase has been trained with text data from the audio transcriptions. Thus, the decoder's language model may not generalize to very different language, for example to spoken daily language with dialects. It may be beneficial to train your own KenLM language model for your domain language and use that in the decoding.

Training data

This model was fine - tuned with 259.57 hours of Finnish transcribed speech data from the following datasets:

Datasets were filtered to include a maximum length of 20 seconds long audio samples.

Training procedure

This model was trained during [Robust Speech Challenge Event](https://discuss.huggingface.co/t/open - to - the - community - robust - speech - recognition - challenge/13614) organized by Hugging Face. Training was done on a Tesla V100 GPU, sponsored by OVHcloud.

Training script was provided by Hugging Face and it is available [here](https://github.com/huggingface/transformers/blob/main/examples/research_projects/robust - speech - event/run_speech_recognition_ctc_bnb.py). We only modified its data loading for our custom datasets.

For the KenLM language model training, we followed the [blog post tutorial](https://huggingface.co/blog/wav2vec2 - with - ngram) provided by Hugging Face. Training data for the 5 - gram KenLM were text transcriptions of the audio training data.

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e - 05
• train_batch_size: 32
• eval_batch_size: 8
• seed: 42
• optimizer: 8 - bit Adam with betas=(0.9,0.999) and epsilon = 1e - 08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 5
• mixed_precision_training: Native AMP

The pretrained facebook/wav2vec2-xls - r - 1b model was initialized with the following hyperparameters:

• attention_dropout: 0.094
• hidden_dropout: 0.047
• feat_proj_dropout: 0.04
• mask_time_prob: 0.082
• layerdrop: 0.041
• activation_dropout: 0.055
• ctc_loss_reduction: "mean"

Training results

Framework versions

• Transformers 4.17.0.dev0
• Pytorch 1.10.2+cu102
• Datasets 1.18.3
• Tokenizers 0.11.0

Evaluation results

Evaluation was done with the [Common Voice 7.0 Finnish test split](https://huggingface.co/datasets/mozilla - foundation/common_voice_7_0).

To evaluate this model, run the eval.py script in this repository:

python3 eval.py --model_id aapot/wav2vec2-xlsr-1b-finnish-lm --dataset mozilla - foundation/common_voice_7_0 --config fi --split test

This model (the second row of the table) achieves the following WER (Word Error Rate) and CER (Character Error Rate) results compared to our other models:

Team Members

• Aapo Tanskanen, Hugging Face profile, LinkedIn profile
• Rasmus Toivanen, Hugging Face profile, LinkedIn profile

Feel free to contact us for more details 🤗

📄 License

This project is licensed under the Apache - 2.0 license.