| | --- |
| | language: |
| | - en |
| | - zh |
| | - de |
| | - es |
| | - ru |
| | - ko |
| | - fr |
| | - ja |
| | - pt |
| | - tr |
| | - pl |
| | - ca |
| | - nl |
| | - ar |
| | - sv |
| | - it |
| | - id |
| | - hi |
| | - fi |
| | - vi |
| | - he |
| | - uk |
| | - el |
| | - ms |
| | - cs |
| | - ro |
| | - da |
| | - hu |
| | - ta |
| | - 'no' |
| | - th |
| | - ur |
| | - hr |
| | - bg |
| | - lt |
| | - la |
| | - mi |
| | - ml |
| | - cy |
| | - sk |
| | - te |
| | - fa |
| | - lv |
| | - bn |
| | - sr |
| | - az |
| | - sl |
| | - kn |
| | - et |
| | - mk |
| | - br |
| | - eu |
| | - is |
| | - hy |
| | - ne |
| | - mn |
| | - bs |
| | - kk |
| | - sq |
| | - sw |
| | - gl |
| | - mr |
| | - pa |
| | - si |
| | - km |
| | - sn |
| | - yo |
| | - so |
| | - af |
| | - oc |
| | - ka |
| | - be |
| | - tg |
| | - sd |
| | - gu |
| | - am |
| | - yi |
| | - lo |
| | - uz |
| | - fo |
| | - ht |
| | - ps |
| | - tk |
| | - nn |
| | - mt |
| | - sa |
| | - lb |
| | - my |
| | - bo |
| | - tl |
| | - mg |
| | - as |
| | - tt |
| | - haw |
| | - ln |
| | - ha |
| | - ba |
| | - jw |
| | - su |
| | tags: |
| | - audio |
| | - automatic-speech-recognition |
| | - hf-asr-leaderboard |
| | - mlx |
| | - speech-to-text |
| | - speech-to-speech |
| | - speech |
| | - speech generation |
| | - stt |
| | widget: |
| | - example_title: Librispeech sample 1 |
| | src: https://cdn-media.huggingface.co/speech_samples/sample1.flac |
| | - example_title: Librispeech sample 2 |
| | src: https://cdn-media.huggingface.co/speech_samples/sample2.flac |
| | pipeline_tag: automatic-speech-recognition |
| | license: apache-2.0 |
| | library_name: mlx-audio |
| | model-index: |
| | - name: whisper-tiny |
| | results: |
| | - task: |
| | type: automatic-speech-recognition |
| | name: Automatic Speech Recognition |
| | dataset: |
| | name: LibriSpeech (clean) |
| | type: librispeech_asr |
| | config: clean |
| | split: test |
| | args: |
| | language: en |
| | metrics: |
| | - type: wer |
| | value: 7.54 |
| | name: Test WER |
| | - task: |
| | type: automatic-speech-recognition |
| | name: Automatic Speech Recognition |
| | dataset: |
| | name: LibriSpeech (other) |
| | type: librispeech_asr |
| | config: other |
| | split: test |
| | args: |
| | language: en |
| | metrics: |
| | - type: wer |
| | value: 17.15 |
| | name: Test WER |
| | - task: |
| | type: automatic-speech-recognition |
| | name: Automatic Speech Recognition |
| | dataset: |
| | name: Common Voice 11.0 |
| | type: mozilla-foundation/common_voice_11_0 |
| | config: hi |
| | split: test |
| | args: |
| | language: hi |
| | metrics: |
| | - type: wer |
| | value: 141 |
| | name: Test WER |
| | --- |
| | |
| | # mlx-community/whisper-tiny-asr-8bit |
| | This model was converted to MLX format from [`openai/whisper-tiny`](https://huggingface.co/openai/whisper-tiny) using mlx-audio version **0.2.10**. |
| | Refer to the [original model card](https://huggingface.co/openai/whisper-tiny) for more details on the model. |
| |
|
| | ## Use with mlx-audio |
| |
|
| | ```bash |
| | pip install -U mlx-audio |
| | ``` |
| |
|
| | ### CLI Example: |
| | ```bash |
| | python -m mlx_audio.stt.generate --model mlx-community/whisper-tiny-asr-8bit --audio "audio.wav" |
| | ``` |
| | ### Python Example: |
| | ```python |
| | from mlx_audio.stt.utils import load_model |
| | from mlx_audio.stt.generate import generate_transcription |
| | model = load_model("mlx-community/whisper-tiny-asr-8bit") |
| | transcription = generate_transcription( |
| | model=model, |
| | audio_path="path_to_audio.wav", |
| | output_path="path_to_output.txt", |
| | format="txt", |
| | verbose=True, |
| | ) |
| | print(transcription.text) |
| | ``` |
| |
|
