Downloads · 30 days
131
11% of all-time downloads
Archime/parakeet-tdt-0.6b-v3-fr-tv-media
parakeet-tdt-0.6b-v3-fr-tv-media is a automatic speech recognition model from Archime. Use it when you need speech turned into text. It is set up for nemo. The card lists the license as cc-by-4.0.
This model is a fine-tuned version of NVIDIA Parakeet-TDT-0.6b-v3 optimized for French spoken in media contexts (Radio, Television, Podcasts).
Downloads · 30 days
131
11% of all-time downloads
All-time downloads
1.1K
Public
Repo size
2.5 GB
Likes
3
Public
Click a slice to open those files.
.nemo2.5 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of NVIDIA Parakeet-TDT-0.6b-v3 optimized for French spoken in media contexts (Radio, Television, Podcasts).
It leverages the Token-and-Duration Transducer (TDT) architecture, which provides an exceptional balance between the high accuracy of classic Transducers and the inference speed of non-autoregressive models, thanks to its efficient prediction of token durations.
To use this model, you must have the NVIDIA NeMo toolkit installed.
pip install nemo_toolkit['all']==2.6.1
import nemo.collections.asr as nemo_asr
# Load the model from Hugging Face
model = nemo_asr.models.ASRModel.from_pretrained("Archime/parakeet-tdt-0.6b-v3-fr-tv-media")
# Transcribe an audio file
transcription = model.transcribe(["path/to/your_audio.wav"])
print(transcription)
Note: Results depend on audio quality and the specific media domain.
The fine-tuning process specifically targeted the nuances of French media speech, including spontaneous dialogue, interviews, and broadcast-quality audio.

The following table compares the Base Model vs. this Fine-tuned version. All scores are in decimal format (e.g., 0.0445 = 4.45% WER).
| Dataset | Mode | Base WER | Fine-tuned WER | Improvement |
|---|---|---|---|---|
| News (Info) | Processed | 0.1042 | 0.0445 | -57% |
| Documentaries | Processed | 0.0863 | 0.0380 | -56% |
| Society (Talks) | Processed | 0.1224 | 0.0488 | -60% |
| Sports | Processed | 0.1187 | 0.0845 | -29% |
| Entertainment | Processed | 0.1174 | 0.0662 | -43% |
| Fleurs (FR) | Processed | 0.0871 | 0.0874 | Stable |
| Fleurs (EN) | Processed | 0.0753 | 0.1716 | Degradation |
While this model excels in media contexts, users should be aware of the following limitations:
To optimize this model for French media while preserving the robust acoustic grounding of the original model, a parameter freezing strategy was applied.
eval mode. This preserves universal sound and phoneme understanding, preventing catastrophic forgetting.| Component | Type | Parameters | Mode |
|---|---|---|---|
| Preprocessor | AudioToMelSpectrogram | 0 | Train |
| Encoder | ConformerEncoder | 608 M | EVAL (Frozen) |
| Decoder | RNNTDecoder | 11.8 M | TRAIN |
| Joint | RNNTJoint | 6.3 M | TRAIN |
| Loss | RNNTLoss | 0 | Train |
| Spec_augmentation | SpectrogramAugmentation | 0 | Train |
This model was specifically fine-tuned on the Archime/french_tv_media_dataset_2026 dataset.
The dataset consists of 5 major thematic streams, which were carefully balanced during the fine-tuning process to ensure broad coverage of the media landscape:
This diversity enables the model to be robust across various linguistic registers—ranging from the formal, scripted language of documentaries to the spontaneous (and often noisy) speech found in entertainment and live sports.
To reproduce the metrics displayed in the performance table, ensure you have NVIDIA NeMo installed and use the official evaluation scripts.
You can adjust the text processing flags to toggle between Raw and Normalized scores.
pip install -r script/requirements.txt
python script/prepare_datasets_test_NeMo.py
python script/speech_to_text_eval_manifests.py \
+models="{parakeet-tdt-0.6b-v3:'nvidia/parakeet-tdt-0.6b-v3',parakeet-tdt-0.6b-v3-fr-tv-media:'Archime/parakeet-tdt-0.6b-v3-fr-tv-media'}" \
+dataset_manifests.fleurs_fr_fr="pathto/nemo_datasets/fleurs/fleurs_test_manifest.json" \
+dataset_manifests.info="pathto/nemo_datasets/french_tv_media_dataset_2026/archime_test_info_manifest.json" \
+dataset_manifests.societe="pathto/nemo_datasets/french_tv_media_dataset_2026/archime_test_societe_manifest.json" \
+dataset_manifests.divertissements="pathto/nemo_datasets/french_tv_media_dataset_2026/archime_test_divertissements_manifest.json" \
+dataset_manifests.documentaires="pathto/nemo_datasets/french_tv_media_dataset_2026/archime_test_documentaires_manifest.json" \
+dataset_manifests.sports="pathto/nemo_datasets/french_tv_media_dataset_2026/archime_test_sports_manifest.json" \
use_cer=True \
batch_size=32
If you use this model in your research or product, please cite the original Parakeet-TDT work and this fine-tuned version:
Base model:
@misc{parakeet-tdt-0.6b-v3,
author = {NVIDIA},
title = {Parakeet-TDT-0.6B},
year = {2024},
publisher = {HuggingFace},
url = {https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3}
}
@misc{parakeet_tdt_french_tv_2026,
author = {Archime},
title = {Parakeet-TDT-0.6b-French-TV-Media},
year = {2026},
publisher = {Hugging Face},
journal = {Hugging Face Model Hub},
howpublished = {\url{[https://huggingface.co/Archime/parakeet-tdt-0.6b-v3-fr-tv-media](https://huggingface.co/Archime/parakeet-tdt-0.6b-v3-fr-tv-media)}}
}
For questions or issues, please open an issue on the repository.