Skip to page content
SAVRN
Search Plan a project

Open-weight model · Speech recognition

wav2vec2-xls-r-300m-cv7-turkish

by Muhammet Poyraz mpoyraz/wav2vec2-xls-r-300m-cv7-turkish

wav2vec2-xls-r-300m-cv7-turkish is an open-weight model for speech recognition from Muhammet Poyraz, released under Creative Commons Attribution 4.0. Its published files total 1.8 GB. It draws 1.1M downloads a month.

This ASR model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on Turkish language. The following datasets were used for finetuning: - Common Voice 7.0 TR All validated split except test split was used for training.

Parameters—
Context—
Weights1.8 GB
Licensecc-by-4.0
AccessOpen weights
Monthly Downloads1.1M

Model Card

By Muhammet Poyraz, published under cc-by-4.0, revision 708639f50559.

This ASR model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on Turkish language. The following datasets were used for finetuning: - Common Voice 7.0 TR All validated split except test split was used for training. To support both of the datasets above, custom pre-processing and loading steps was performed and wav2vec2-turkish repo was used for that purpose. The following hypermaters were used for finetuning: - learningrate 2e-4 - numtrainepochs 10 - warmupsteps 500 - freezefeatureextractor - masktimeprob 0.1 - maskfeatureprob 0.05 - featprojdropout 0.05 - attentiondropout 0.05 - finaldropout 0.05 - activationdropout 0.05 - perdevicetrainbatchsize 8 - perdeviceevalbatchsize 8…

Read Muhammet Poyraz's full model card

Model description

This ASR model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on Turkish language.

Training and evaluation data

The following datasets were used for finetuning: - Common Voice 7.0 TR All validated split except test split was used for training. - MediaSpeech

Training procedure

To support both of the datasets above, custom pre-processing and loading steps was performed and wav2vec2-turkish repo was used for that purpose.

Training hyperparameters

The following hypermaters were used for finetuning: - learning_rate 2e-4 - num_train_epochs 10 - warmup_steps 500 - freeze_feature_extractor - mask_time_prob 0.1 - mask_feature_prob 0.05 - feat_proj_dropout 0.05 - attention_dropout 0.05 - final_dropout 0.05 - activation_dropout 0.05 - per_device_train_batch_size 8 - per_device_eval_batch_size 8 - gradient_accumulation_steps 8

Framework versions

  • Transformers 4.16.0.dev0
  • Pytorch 1.10.1
  • Datasets 1.17.0
  • Tokenizers 0.10.3

Language Model

N-gram language model is trained on a Turkish Wikipedia articles using KenLM and ngram-lm-wiki repo was used to generate arpa LM and convert it into binary format.

Evaluation Commands

Please install unicode_tr package before running evaluation. It is used for Turkish text processing. 1. To evaluate on mozilla-foundation/common_voice_7_0 with split test

python eval.py --model_id mpoyraz/wav2vec2-xls-r-300m-cv7-turkish --dataset mozilla-foundation/common_voice_7_0 --config tr --split test
  1. To evaluate on speech-recognition-community-v2/dev_data
python eval.py --model_id mpoyraz/wav2vec2-xls-r-300m-cv7-turkish --dataset speech-recognition-community-v2/dev_data --config tr --split validation --chunk_length_s 5.0 --stride_length_s 1.0

Evaluation results:

Dataset WER CER
Common Voice 7 TR test split 8.62 2.26
Speech Recognition Community dev data 30.87 10.69

Configuration

Architecture
Wav2Vec2ForCTC
Layers
24
Hidden size
1,024
Feed-forward size
4,096
Attention heads
16
Vocabulary size
38
Stored precision
float32
Model type
wav2vec2

Identity and Version

Repository
mpoyraz/wav2vec2-xls-r-300m-cv7-turkish
Publisher
Muhammet Poyraz
Task
Speech recognition
Modality
Audio
Library
transformers
Parameters
Not stated by the source
Languages
tr
Revision
708639f50559d7970f462e13ec64d3f059ca89f6
First published
2022-03-02
Last updated
2022-03-23

Files and Weights

13 files, 1.8 GB in total. The weights are 2 files totalling 1.8 GB in bin.

Weights2 files · 1.8 GB
Configuration6 files · 7.9 KB
Tokenizer2 files · 532 B
Documentation1 file · 3.6 KB
Other1 file · 5.4 MB
Repository1 file · 1.2 KB
Every file
FileTypeSizeSHA-256
language_model/lm.binWeights496.1 MB ca3b400bd46d
pytorch_model.binWeights1.3 GB 008d69c82bf4
alphabet.jsonConfiguration232 B —
config.jsonConfiguration2.0 KB —
eval.pyConfiguration5.2 KB —
language_model/attrs.jsonConfiguration78 B —
preprocessor_config.jsonConfiguration260 B —
special_tokens_map.jsonConfiguration85 B —
README.mdDocumentation3.6 KB —
language_model/unigrams.txtOther5.4 MB —
.gitattributesRepository1.2 KB —
tokenizer_config.jsonTokenizer181 B —
vocab.jsonTokenizer351 B —

License and Download

License
cc-by-4.0
Access
Open weights, no gate
Download size
1.8 GB
Download from Muhammet Poyraz

Released by Muhammet Poyraz through its official repository on Hugging Face. Read the license.

Built From

  • Trained on (disclosed) mozilla-foundation/common_voice_7_0

Evaluations

Each result is shown as reported, with the conditions its reporter stated. None is a SAVRN measurement. A comparison lines two results up only when their configuration, unit and setup are all stated and identical.

BenchmarkConditionsResultReported byRevisionDate
Common Voice 7 Task Automatic Speech RecognitionMetric Test CERComparison conditions not established 2.26 mpoyraz
Publisher reported		 Evaluated revision not stated —
Common Voice 7 Task Automatic Speech RecognitionMetric Test WERComparison conditions not established 8.62 mpoyraz
Publisher reported		 Evaluated revision not stated —
Robust Speech Event - Dev Data Task Automatic Speech RecognitionMetric Test CERComparison conditions not established 10.69 mpoyraz
Publisher reported		 Evaluated revision not stated —
Robust Speech Event - Dev Data Task Automatic Speech RecognitionMetric Test WERComparison conditions not established 30.87 mpoyraz
Publisher reported		 Evaluated revision not stated —
Robust Speech Event - Test Data Task Automatic Speech RecognitionMetric Test WERComparison conditions not established 32.09 mpoyraz
Publisher reported		 Evaluated revision not stated —

Memory Requirements

PrecisionWeights in memory
As published1.8 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About wav2vec2-xls-r-300m-cv7-turkish

Can I use wav2vec2-xls-r-300m-cv7-turkish commercially?

Yes. wav2vec2-xls-r-300m-cv7-turkish is released under Creative Commons Attribution 4.0. CC BY 4.0 permits sharing and adapting the work, including commercially, provided the creator is credited and changes are indicated.

Similar Models

Model · Speech recognition

wav2vec2-large-xlsr-53-japanese

Jonatas Grosman

Fine-tuned facebook/wav2vec2-large-xlsr-53 on Japanese using the train and validation splits of Common Voice 6.1, CSS10 and JSUT. When using this model, make sure that your speech input is sampled at 16kHz. This model has been fine-tuned thanks to the GPU credits generously given by the OVHcloud:) The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint The model can be used directly (without a language model) as follows... Using the HuggingSound library: The model can be evaluated as follows on the Japanese test data of Common Voice. In the table below I report the Word Error Rate (WER) and the Character Error Rate (CER) of the model. I ran the…

Open weights apache-2.0 transformers
View model

Model · Speech recognition

whisperkit-coreml

Argmax

WhisperKit is part of Argmax OSS, an On-device Speech AI SDK for Apple Silicon: https://github.com/argmaxinc/argmax-oss-swift Check out the WhisperKit paper and presentation from ICML 2025: https://icml.cc/virtual/2025/47854 For real-time transcription with speakers and custom vocabulary, check out Argmax Pro SDK: https://www.argmaxinc.com/blog/argmax-sdk-2

Open weights mit whisperkit
View model

Model · Speech recognition

speaker-diarization-3.1

Pyannote

Using this open-source model in production? Consider switching to pyannoteAI for better and faster options. This pipeline is the same as pyannote/speaker-diarization-3.0 except it removes the problematic use of onnxruntime. Both speaker segmentation and embedding now run in pure PyTorch. This should ease deployment and possibly speed up inference. It requires pyannote.audio version 3.1 or higher. It ingests mono audio sampled at 16kHz and outputs speaker diarization as an Annotation instance: - stereo or multi-channel audio files are automatically downmixed to mono by averaging the channels. - audio files sampled at a different rate are resampled to 16kHz automatically upon loading. 1.…

Access requested at publisher mit pyannote-audio
View model

Model · Speech recognition

speaker-diarization-community-1

Pyannote

This pipeline ingests mono audio sampled at 16kHz and outputs speaker diarization. - stereo or multi-channel audio files are automatically downmixed to mono by averaging the channels. - audio files sampled at a different rate are resampled to 16kHz automatically upon loading. The main improvements brought by Community-1 are: - improved speaker assignment and counting - simpler reconciliation with transcription timestamps with exclusive speaker diarization - easy offline use (i.e. without internet connection) - (optionally) hosted on pyannoteAI cloud 1. pip install pyannote.audio 3. Create access token at hf.co/settings/tokens. Out of the box, Community-1 is much better than…

Access requested at publisher cc-by-4.0 pyannote-audio
View model

Model · Speech recognition

faster-whisper-small

Systran

This repository contains the conversion of openai/whisper-small to the CTranslate2 model format. This model can be used in CTranslate2 or projects based on CTranslate2 such as faster-whisper. The original model was converted with the following command: Note that the model weights are saved in FP16. This type can be changed when the model is loaded using the computetype option in CTranslate2. For more information about the original model, see its model card.

Open weights mit ctranslate2
View model

Fine-tuned facebook/wav2vec2-large-xlsr-53 on Portuguese using the train and validation splits of Common Voice 6.1. When using this model, make sure that your speech input is sampled at 16kHz. This model has been fine-tuned thanks to the GPU credits generously given by the OVHcloud:) The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint The model can be used directly (without a language model) as follows... Using the HuggingSound library: 1. To evaluate on mozilla-foundation/commonvoice60 with split test 2. To evaluate on speech-recognition-community-v2/devdata If you want to cite this model you can use this

Open weights apache-2.0 transformers
View model