-
Open ASR Leaderboard configuration for Transformers š¤ models
šNormalize and clean text data for evaluation
-
Open ASR Leaderboard configuration for NVIDIA NeMo ASR models
šNormalize text to a consistent, clean format
-
Open ASR Leaderboard configuration for Boson's Higgs Audio v3
šNormalize and clean text data for analysis
-
Open ASR Leaderboard configuration for API models
šRun model evaluation and get performance metrics
AI & ML interests
None defined yet.
Recent Activity
Papers
View all PapersA collection of ASR models supported in š¤ Transformers
-
openai/whisper-large-v2
Automatic Speech Recognition ā¢ 2B ā¢ Updated ā¢ 125k ā¢ 1.8k -
facebook/wav2vec2-base-960h
Automatic Speech Recognition ā¢ 94.4M ā¢ Updated ā¢ 1.59M ā¢ 398 -
facebook/wav2vec2-large-xlsr-53
Updated ā¢ 416k ā¢ 162 -
facebook/hubert-xlarge-ls960-ft
Automatic Speech Recognition ā¢ 1.0B ā¢ Updated ā¢ 12.7k ā¢ 16
A collection of audio classification models supported in š¤ Transformers
A collection of codec and embedding models supported in š¤ Transformers.
-
laion/clap-htsat-unfused
Feature Extraction ā¢ Updated ā¢ 364k ā¢ ā¢ 76 -
facebook/encodec_32khz
Feature Extraction ā¢ 59M ā¢ Updated ā¢ 47.5k ā¢ 18 -
descript/dac_44khz
Feature Extraction ā¢ 76.6M ā¢ Updated ā¢ 200k ā¢ ā¢ 11 -
descript/dac_24khz
Feature Extraction ā¢ 74.7M ā¢ Updated ā¢ 4.52k ā¢ ā¢ 3
Transformer supported versions of X-Codec models: https://github.com/zhenye234/xcodec?tab=readme-ov-file#available-models
-
hf-audio/xcodec-hubert-general-balanced
Feature Extraction ā¢ 0.2B ā¢ Updated ā¢ 896 ā¢ 2 -
hf-audio/xcodec-wavlm-more-data
Feature Extraction ā¢ 0.2B ā¢ Updated ā¢ 2.16k ā¢ 1 -
hf-audio/xcodec-wavlm-mls
Feature Extraction ā¢ 0.2B ā¢ Updated ā¢ 978 -
hf-audio/xcodec-hubert-general
Feature Extraction ā¢ 0.2B ā¢ Updated ā¢ 1.8k
A collection of TTS models supported in š¤ Transformers.
A collection of music generation models supported in š¤ Transformers and š§Ø Diffusers
-
Open ASR Leaderboard configuration for Transformers š¤ models
šNormalize and clean text data for evaluation
-
Open ASR Leaderboard configuration for NVIDIA NeMo ASR models
šNormalize text to a consistent, clean format
-
Open ASR Leaderboard configuration for Boson's Higgs Audio v3
šNormalize and clean text data for analysis
-
Open ASR Leaderboard configuration for API models
šRun model evaluation and get performance metrics
Transformer supported versions of X-Codec models: https://github.com/zhenye234/xcodec?tab=readme-ov-file#available-models
-
hf-audio/xcodec-hubert-general-balanced
Feature Extraction ā¢ 0.2B ā¢ Updated ā¢ 896 ā¢ 2 -
hf-audio/xcodec-wavlm-more-data
Feature Extraction ā¢ 0.2B ā¢ Updated ā¢ 2.16k ā¢ 1 -
hf-audio/xcodec-wavlm-mls
Feature Extraction ā¢ 0.2B ā¢ Updated ā¢ 978 -
hf-audio/xcodec-hubert-general
Feature Extraction ā¢ 0.2B ā¢ Updated ā¢ 1.8k
A collection of ASR models supported in š¤ Transformers
-
openai/whisper-large-v2
Automatic Speech Recognition ā¢ 2B ā¢ Updated ā¢ 125k ā¢ 1.8k -
facebook/wav2vec2-base-960h
Automatic Speech Recognition ā¢ 94.4M ā¢ Updated ā¢ 1.59M ā¢ 398 -
facebook/wav2vec2-large-xlsr-53
Updated ā¢ 416k ā¢ 162 -
facebook/hubert-xlarge-ls960-ft
Automatic Speech Recognition ā¢ 1.0B ā¢ Updated ā¢ 12.7k ā¢ 16
A collection of TTS models supported in š¤ Transformers.
A collection of audio classification models supported in š¤ Transformers
A collection of music generation models supported in š¤ Transformers and š§Ø Diffusers
A collection of codec and embedding models supported in š¤ Transformers.
-
laion/clap-htsat-unfused
Feature Extraction ā¢ Updated ā¢ 364k ā¢ ā¢ 76 -
facebook/encodec_32khz
Feature Extraction ā¢ 59M ā¢ Updated ā¢ 47.5k ā¢ 18 -
descript/dac_44khz
Feature Extraction ā¢ 76.6M ā¢ Updated ā¢ 200k ā¢ ā¢ 11 -
descript/dac_24khz
Feature Extraction ā¢ 74.7M ā¢ Updated ā¢ 4.52k ā¢ ā¢ 3