---
language:
- "fr"
tags:
- "audio"
- "speech"
- "automatic-speech-recognition"
- "medkit"
- "speechbrain"
datasets:
- "common_voice"
- "pxcorpus"
- "simsamu"
metrics:
- "wer"
---

# Simsamu transcription model

This repository contains a pretrained
[speechbrain](https://github.com/speechbrain/speechbrain) transcription model
for the french language that was fine-tuned on the
[Simsamu](https://huggingface.co/datasets/medkit/simsamu) dataset.

The model is a CTC-based model on top of
[wav2vec2](https://huggingface.co/LeBenchmark/wav2vec2-FR-7K-large) embeddings,
trained on data from the [CommonVoice](https://commonvoice.mozilla.org),
[PxCorpus](https://zenodo.org/records/6482587) and Simsamu datasets. The CTC
layers were trained from scratch and the wav2vec2 layers were fine-tuned.

The model can be used in [medkit](https://github.com/medkit-lib/medkit/) the
following way:

```
from medkit.core.audio import AudioDocument
from medkit.audio.segmentation.pa_speaker_detector import PASpeakerDetector
from medkit.audio.transcription.sb_transcriber import SBTranscriber

# init speaker detector operation
speaker_detector = PASpeakerDetector(
    model="medkit/simsamu-diarization",
    device=0,
    segmentation_batch_size=10,
    embedding_batch_size=10,
)

# init transcriber operation
transcriber = SBTranscriber(
    model="medkit/simsamu-transcription",
    needs_decoder=False,
    output_label="transcription",
    device=0,
    batch_size=10,
)

# create audio document
audio_doc = AudioDocument.from_file("path/to/audio.wav")

# apply speaker detector operation on audio document
# to get speech segments
speech_segments = speaker_detector.run([audio_doc.raw_segment])

# apply transcriber operation on speech segments
transcriber.run(speech_segments)

# display transcription for each speech turn
for speech_seg in speech_segments:
    transcription_attr = speech_seg.attrs.get(label="transcription")[0]
    print(speech_seg.span.start, speech_seg.span.end, transcription_attr.value)
```

More info at https://medkit.readthedocs.io/

See also: [Simsamu diarization
pipeline](https://huggingface.co/medkit/simsamu-diarization)