Automatic Speech Recognition
Transformers
Safetensors
joint_aed_ctc_speech-encoder-decoder
custom_code
Instructions to use BUT-FIT/ED-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BUT-FIT/ED-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="BUT-FIT/ED-base", trust_remote_code=True)# Load model directly from transformers import AutoModelForSpeechSeq2Seq model = AutoModelForSpeechSeq2Seq.from_pretrained("BUT-FIT/ED-base", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
| from transformers import AutoConfig, AutoModelForCausalLM, SpeechEncoderDecoderConfig | |
| from .auto_wrappers import CustomAutoModelForCTC | |
| from .e_branchformer import Wav2Vec2EBranchformerConfig, Wav2Vec2EBranchformerForCTC | |
| from .multi_head_gpt2 import GPT2LMMultiHeadModel, GPT2MultiHeadConfig | |
| from .residual_clasiffier_gpt2 import ( | |
| GPT2ResidualsLMHeadConfig, | |
| GPT2ResidualsLMHeadModel, | |
| ) | |
| AutoConfig.register("gpt2-multi-head", GPT2MultiHeadConfig) | |
| AutoModelForCausalLM.register(GPT2MultiHeadConfig, GPT2LMMultiHeadModel) | |
| AutoConfig.register("gpt2-residuals-head", GPT2ResidualsLMHeadConfig) | |
| AutoModelForCausalLM.register(GPT2ResidualsLMHeadConfig, GPT2ResidualsLMHeadModel) | |
| AutoConfig.register("wav2vec2-ebranchformer", Wav2Vec2EBranchformerConfig) | |
| CustomAutoModelForCTC.register(Wav2Vec2EBranchformerConfig, Wav2Vec2EBranchformerForCTC) | |
| class JointCTCAttentionEncoderDecoderConfig(SpeechEncoderDecoderConfig): | |
| model_type = "joint_aed_ctc_speech-encoder-decoder" | |
| is_composition = True | |