Automatic Speech Recognition
Transformers
PyTorch
TensorFlow
JAX
Safetensors
Portuguese
English
Spanish
whisper
audio
Eval Results (legacy)
Instructions to use cloudqi/cqi_speech_recognize_pt_v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cloudqi/cqi_speech_recognize_pt_v0 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="cloudqi/cqi_speech_recognize_pt_v0")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("cloudqi/cqi_speech_recognize_pt_v0") model = AutoModelForSpeechSeq2Seq.from_pretrained("cloudqi/cqi_speech_recognize_pt_v0", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from cloudqi/cqi_speech_recognize_pt_v0: direct link, hf CLI and curl.
- Browser
- Download file 1.4 kB
-
https://huggingface.co/cloudqi/cqi_speech_recognize_pt_v0/resolve/main/README.md
- Command line
-
hf download hf://cloudqi/cqi_speech_recognize_pt_v0/README.md
-
curl -L -o README.md https://huggingface.co/cloudqi/cqi_speech_recognize_pt_v0/resolve/main/README.md
1.4 kB
| language: | |
| - pt | |
| - en | |
| - es | |
| tags: | |
| - audio | |
| - automatic-speech-recognition | |
| widget: | |
| - example_title: Exemplo 1 | |
| src: https://huggingface.co/proxy/cdn-media.huggingface.co/speech_samples/sample1.flac | |
| model-index: | |
| - name: cqi_speech_recognize_pt_v0 | |
| results: | |
| - task: | |
| name: Automatic Speech Recognition | |
| type: automatic-speech-recognition | |
| dataset: | |
| name: LibriSpeech (clean) | |
| type: librispeech_asr | |
| config: clean | |
| split: test | |
| args: | |
| language: pt | |
| metrics: | |
| - name: Test WER | |
| type: wer | |
| value: 2.9 | |
| - task: | |
| name: Automatic Speech Recognition | |
| type: automatic-speech-recognition | |
| dataset: | |
| name: LibriSpeech (other) | |
| type: librispeech_asr | |
| config: other | |
| split: test | |
| args: | |
| language: pt | |
| metrics: | |
| - name: Test WER | |
| type: wer | |
| value: 5.9 | |
| - task: | |
| name: Automatic Speech Recognition | |
| type: automatic-speech-recognition | |
| dataset: | |
| name: Common Voice 11.0 | |
| type: mozilla-foundation/common_voice_11_0 | |
| config: hi | |
| split: test | |
| args: | |
| language: hi | |
| metrics: | |
| - name: Test WER | |
| type: wer | |
| value: 53.87 | |
| pipeline_tag: automatic-speech-recognition | |
| license: apache-2.0 | |
| datasets: | |
| - cloudqi/abreviacoes_e_girias_pt_v0 | |
| # Voice Transcript - Portuguese Focused (From Whisper) | |
| Optimized to work with Brazilian Language. | |
| Current Version: v0.1 |