hailin
/
it0
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix(stt): always use Whisper auto language detection, remove app language hint 

Whisper detects language from audio content — speaks Chinese gets Chinese,
speaks English gets English. App language setting is irrelevant to STT.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
hailin 2026-03-07 00:03:58 -08:00
parent 4c7c05eb37
commit ecc64e0ff9
3 changed files with 6 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
it0_app/lib/features/chat/data/datasources/chat_remote_datasource.dart
View File

@ -153,20 +153,16 @@ class ChatRemoteDatasource {
/// Uploads an audio file to the voice-message endpoint. /// Uploads an audio file to the voice-message endpoint.
/// Backend performs STT, interrupts any running task if needed, and /// Backend performs STT, interrupts any running task if needed, and
/// Transcribe audio to text (STT only, does NOT send to agent). /// Transcribe audio to text (STT only, does NOT send to agent).
/// Returns the transcript string. /// No language hint is sent — Whisper auto-detects from audio content.
/// Pass language='auto' to let Whisper auto-detect (best for mixed-language).
Future<String> transcribeAudio({ Future<String> transcribeAudio({
required String audioPath, required String audioPath,
String language = 'zh',
}) async { }) async {
final fields = <String, dynamic>{ final formData = FormData.fromMap({
'audio': await MultipartFile.fromFile( 'audio': await MultipartFile.fromFile(
audioPath, audioPath,
filename: audioPath.split('/').last, filename: audioPath.split('/').last,
), ),
}; });
if (language != 'auto') fields['language'] = language;
final formData = FormData.fromMap(fields);
final response = await _dio.post( final response = await _dio.post(
'${ApiEndpoints.agent}/transcribe', '${ApiEndpoints.agent}/transcribe',
data: formData, data: formData,

4
it0_app/lib/features/chat/presentation/pages/chat_page.dart
View File

@ -13,7 +13,6 @@ import '../widgets/approval_action_card.dart';
import '../widgets/conversation_drawer.dart'; import '../widgets/conversation_drawer.dart';
import '../../../agent_call/presentation/pages/agent_call_page.dart'; import '../../../agent_call/presentation/pages/agent_call_page.dart';
import '../widgets/voice_mic_button.dart'; import '../widgets/voice_mic_button.dart';
import '../../../settings/presentation/providers/settings_providers.dart';
// --------------------------------------------------------------------------- // ---------------------------------------------------------------------------
// Chat page – Timeline workflow style (inspired by Claude Code VSCode) // Chat page – Timeline workflow style (inspired by Claude Code VSCode)
@ -62,8 +61,7 @@ class _ChatPageState extends ConsumerState<ChatPage> {
_messageController.text = '识别中…'; _messageController.text = '识别中…';
}); });
try { try {
final language = ref.read(settingsProvider).language; final text = await ref.read(chatProvider.notifier).transcribeAudio(audioPath);
final text = await ref.read(chatProvider.notifier).transcribeAudio(audioPath, language: language);
if (mounted) { if (mounted) {
setState(() { setState(() {
_messageController.text = text; _messageController.text = text;

4
it0_app/lib/features/chat/presentation/providers/chat_providers.dart
View File

@ -573,9 +573,9 @@ class ChatNotifier extends StateNotifier<ChatState> {
} }
} }
Future<String> transcribeAudio(String audioPath, {String language = 'zh'}) async { Future<String> transcribeAudio(String audioPath) async {
final datasource = _ref.read(chatRemoteDatasourceProvider); final datasource = _ref.read(chatRemoteDatasourceProvider);
return datasource.transcribeAudio(audioPath: audioPath, language: language); return datasource.transcribeAudio(audioPath: audioPath);
} }
Future<void> cancelCurrentTask() async { Future<void> cancelCurrentTask() async {