common-voice-pt-batch
v1.0.0
openCC0-1.0scores against whisper-medium-pt-batchgated
Audio
40 utterances · 229.949s total · Hz
Requires a credential
Running this pack needs a personal API key, set via MDC_API_KEY. The goesb run wizard prompts for it and stores it locally — it is never sent to goesb's servers.
Create a free Mozilla Data Collective account at https://mozilladatacollective.com, agree to the Common Voice dataset's terms on its dataset page, then generate an API key from the dashboard (https://mozilladatacollective.com/api-reference). Install the client with `pip install datacollective`, then set MDC_API_KEY to your key.
https://mozilladatacollective.comIntegrity
sha256: 346c1d78fc0aa17f470347197e92667a649aab736ebd89d8c6bcdfe7a8f9ce5f
Full manifest
{
"id": "common-voice-pt-batch",
"version": "1.0.0",
"profile_id": "whisper-medium-pt-batch",
"visibility": "open",
"license": "CC0-1.0",
"metadata": {
"language": "pt-BR",
"recording_environment": "crowd-sourced (variable, personal devices)",
"microphone": "variable (crowd-sourced personal devices)",
"background_noise": "variable",
"speech_style": "read",
"transcription_style": "verbatim",
"tags": [
"common-voice",
"portuguese",
"gated"
],
"num_speakers": 40
},
"audio": {
"count": 40,
"total_duration_s": 229.949,
"manifest_sha256": "5b88c3a82e2e3d4bb64be220868e61d0a0b465044f33af36d9ff1b8ea6bc91b1",
"source": {
"type": "mozilla_data_collective",
"params": {
"dataset_id": "cmqinmnkf00w8nr07hkbbxgw7"
},
"credential": {
"env_var": "MDC_API_KEY",
"signup_url": "https://mozilladatacollective.com",
"instructions": "Create a free Mozilla Data Collective account at https://mozilladatacollective.com, agree to the Common Voice dataset's terms on its dataset page, then generate an API key from the dashboard (https://mozilladatacollective.com/api-reference). Install the client with `pip install datacollective`, then set MDC_API_KEY to your key."
}
}
},
"min_runner_version": "0.5.0",
"sha256": "346c1d78fc0aa17f470347197e92667a649aab736ebd89d8c6bcdfe7a8f9ce5f"
}